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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 19-GEMMASCOPE-2-TRANSCODER-262K
    4. 15241
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_19_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    વાનું
    0.72
    imi
    0.71
     Clearly
    0.69
    ;');
    0.69
     AppMethodBeat
    0.68
    ];
    0.68
     Clear
    0.66
    AppLink
    0.66
    );
    0.65
     Aqui
    0.65
    POSITIVE LOGITS
     Floyd
    0.78
     মজুমদার
    0.77
    -,
    0.73
     GUS
    0.71
    ​,
    0.69
    ndvi
    0.68
     ग़
    0.68
     ၁
    0.68
     vencer
    0.67
     NDP
    0.67
    Activations Density 0.014%

    No Known Activations