© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5587
    Prev
    Next
    INDEX
    Explanations

    ContentView structure definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    й
    1.02
    ''''
    0.81
    indul
    0.77
    whelming
    0.73
     shellcheck
    0.70
    ’’’’
    0.68
    कालीन
    0.67
     digitally
    0.67
    ományos
    0.66
     technically
    0.66
    POSITIVE LOGITS
    وای
    0.78
    isierung
    0.72
     Ө
    0.72
    죵
    0.72
    kommt
    0.71
     ransom
    0.70
    umuz
    0.69
    зова
    0.69
    ızı
    0.69
     siapa
    0.69
    Activations Density 0.001%

    No Known Activations