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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35187
    Prev
    Next
    INDEX
    Explanations

    gangster

    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_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
    '
    0.93
    </h2>
    0.93
    ב
    0.89
    \
    0.88
    ب
    0.83
    </strong>
    0.80
    ม
    0.76
    어
    0.73
    라
    0.70
    مین
    0.70
    POSITIVE LOGITS
     umani
    0.73
     свойства
    0.64
     ladd
    0.63
     человек
    0.60
     вот
    0.60
     университе
    0.60
     привле
    0.60
     ứng
    0.59
     a
    0.58
     americ
    0.58
    Activations Density 0.000%

    No Known Activations