© 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. 5525
    Prev
    Next
    INDEX
    Explanations

    exercises

    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
    с
    1.91
     становится
    1.89
    at
    1.89
    +}$
    1.85
    ≙
    1.82
    phoneNumber
    1.74
    as
    1.74
    疱
    1.73
    ۰
    1.68
    om
    1.68
    POSITIVE LOGITS
    م
    2.43
     equivalently
    2.20
    icrous
    2.05
    うまく
    1.98
    nega
    1.95
    ियों
    1.94
     antagonist
    1.92
    markt
    1.91
     jüng
    1.91
    사이트
    1.87
    Activations Density 0.055%

    No Known Activations