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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5931
    Prev
    Next
    INDEX
    Explanations

    code snippets and data structures, especially those containing brackets and quotes.

    oai_token-act-pair · gemini-2.0-flash

    programming syntax or code endings

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

    Punctuation / brackets

    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
    ValueStyle
    -0.82
    évaluateur
    -0.78
    AntiForgeryToken
    -0.78
    SourceChecksum
    -0.76
    ⓧ
    -0.74
     lenker
    -0.72
    Autoritní
    -0.68
    ьаж
    -0.68
    SharedCtor
    -0.68
    Portale
    -0.67
    POSITIVE LOGITS
    "");
    0.69
    ...');
    0.65
    ])));
    0.62
    ()]);
    0.61
    }';
    0.59
    ...");
    0.59
    ]]);
    0.58
    "}")
    0.57
     />;
    0.56
     />);
    0.56
    Activations Density 4.648%

    No Known Activations