Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5842
    Prev
    Next
    INDEX
    Explanations

    computer code and links

    oai_token-act-pair · gemini-2.0-flash

    code syntax and function calls

    np_token-act-pair-logits · gpt-4o-mini

    code, math, websites

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_21/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    >");
    
    -1.22
    .”)
    -1.04
    >");
    -1.01
     "");
    -0.98
    .")
    
    -0.97
    .");
    
    -0.96
     />);
    -0.95
    """)
    -0.94
    "):
    
    -0.94
     "");
    
    -0.93
    POSITIVE LOGITS
    </blockquote>
    0.59
    "))
    0.46
    '))
    0.46
    ))
    0.44
    )))
    0.39
    »?
    0.39
    )):
    0.38
    )){
    0.37
     ))
    0.34
     live
    0.34
    Activations Density 3.767%

    No Known Activations