© 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-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261169
    Prev
    Next
    INDEX
    Explanations

    性描写 or 性暴力

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-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
    f
    2.06
    b
    1.86
    ak
    1.77
    p
    1.77
    ب
    1.66
    ي
    1.55
    r
    1.55
    is
    1.52
    i
    1.49
    l
    1.49
    POSITIVE LOGITS
     می
    1.16
    い
    1.10
    ті
    1.07
    тно
    1.02
    প্যাথ
    0.99
    тному
    0.98
    ्स
    0.97
    apanicola
    0.97
     mosques
    0.95
     pravo
    0.95
    Activations Density 0.000%

    No Known Activations