© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3541
    Prev
    Next
    INDEX
    Explanations

    wiki URLs

    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_5_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
    स
    2.09
    里昂
    1.95
    NOVEMBER
    1.92
     Allerdings
    1.87
    не
    1.86
     Jill
    1.84
    ड
    1.83
    𝗳
    1.83
     nCenters
    1.82
     Sigh
    1.81
    POSITIVE LOGITS
     overt
    1.71
    प्रधान
    1.69
    fär
    1.60
    ä
    1.55
    z
    1.54
    plicial
    1.52
    eer
    1.51
     p
    1.50
     boon
    1.46
    лган
    1.44
    Activations Density 0.002%

    No Known Activations