Watch your words flow through tokenization, embeddings, attention, and feed-forward layers — animated step by step.
Last Updated: April 2026
Transformer Visualizer is a free educational tool that helps users understand how transformer neural networks process language. We are committed to protecting your privacy.
If you provide your own API key:
Anthropic API: When you use your own API key, your text is sent directly to Anthropic's Claude API. Please refer to Anthropic's Privacy Policy for how they handle data.
Google Fonts: We use Google Fonts for typography. Google may collect basic usage data.
We use localStorage (browser storage) to save your API key locally on your device. This is not a cookie and never leaves your browser.
Questions about this privacy policy? Contact: dehatianimator@gmail.com
In Short: We don't collect your data. Your API key stays in your browser. The text you visualize goes directly to Anthropic's API using your key.
Last Updated: April 2026
By accessing and using Transformer Visualizer, you accept and agree to be bound by these Terms of Use.
Transformer Visualizer is a free educational tool that provides interactive visualizations of how transformer neural networks process language.
API Key Security:
Acceptable Use:
This service is provided free of charge for educational purposes. We make no guarantees about uptime, accuracy, or compatibility.
This tool uses the Anthropic Claude API. Your use of the API is subject to Anthropic's Terms of Service.
Educational Purpose Only: This tool is for educational visualization only. The visualizations are simplified representations.
No Warranty: This service is provided "as is" without warranties of any kind.
Important: You are responsible for all costs associated with your Anthropic API usage. Each visualization uses approximately 50-150 tokens.
Questions about these terms? Contact: dehatianimator@gmail.com
In Short: This is a free educational tool. You provide your own API key and pay for your own API usage. Use responsibly.
Last Updated: April 2026
Transformer Visualizer is an open educational project created to help people understand how transformer neural networks process language through interactive visualizations.
MIT License - This project is released under the MIT License, which means you're free to use, modify, and distribute the code with attribution.
✓ Freely allowed:
If you use or modify this code, please provide attribution by including credit in your project documentation.
The complete source code is available on GitHub: github.com/yourusername/transformer-visualizer
This code is provided "as is" without warranty of any kind. See the full MIT License for details.
Teachers, professors, and educators are especially encouraged to use and adapt this tool for their courses. No special permission needed - just attribution!
Yes, you can use this in commercial projects! The MIT License allows commercial use. Just include the attribution notice.
Questions about licensing? Contact: your-email@example.com
In Short: Free to use, modify, and distribute with attribution. MIT License. Open source on GitHub.