© 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. 5484
    Prev
    Next
    INDEX
    Explanations

    driving force behind

    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
     espress
    2.68
    勹
    2.57
    গ
    2.55
     absolument
    2.45
     Möglich
    2.36
    Т
    2.25
     reckoned
    2.24
     legge
    2.23
     मुताबिक
    2.20
     exped
    2.14
    POSITIVE LOGITS
    وب
    2.31
    л
    2.27
    spaper
    2.13
    я
    2.06
    鸯
    2.05
     blame
    1.96
    ק
    1.95
    ceva
    1.94
    isnan
    1.93
     вікі
    1.92
    Activations Density 0.014%

    No Known Activations