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. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 9479
    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_31_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
    Czas
    0.67
    惺
    0.67
     unnecessarily
    0.65
     plass
    0.62
    PE
    0.62
    Smooth
    0.61
    पे
    0.61
     cih
    0.61
     needlessly
    0.60
    菊花
    0.60
    POSITIVE LOGITS
     rent
    0.67
    երը
    0.64
    かり
    0.63
    이가
    0.62
    joni
    0.62
    聲
    0.60
     effected
    0.60
    タミン
    0.60
     წინ
    0.59
     कस्बे
    0.59
    Activations Density 0.190%

    No Known Activations