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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1588
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and equations, especially those used in physics papers

    oai_token-act-pair · gemini-2.0-flash

    mathematical notation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/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
    };*/
    -0.23
    )++;
    -0.21
    ?");
    -0.20
    >");
    
    -0.19
    /");
    -0.18
    !");
    
    -0.17
    %")
    -0.16
    /';
    -0.16
     "/";
    -0.16
    /');
    -0.16
    POSITIVE LOGITS
     purpoſe
    0.74
     raiſ
    0.74
    <unused47>
    0.72
    <unused43>
    0.72
    <unused8>
    0.72
    <unused6>
    0.72
    <unused14>
    0.72
    <unused16>
    0.72
    <pad>
    0.72
    <unused3>
    0.72
    Activations Density 1.967%

    No Known Activations