© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 206120
    Prev
    Next
    INDEX
    Explanations

    what am i

    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_10_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
     (
    0.72
     name
    0.64
     eup
    0.64
     Política
    0.62
     Callahan
    0.62
     &
    0.61
     λό
    0.61
     floral
    0.60
    -
    0.60
     see
    0.59
    POSITIVE LOGITS
    ج
    0.92
    ق
    0.88
    ac
    0.87
    기
    0.86
    ag
    0.86
    ０
    0.85
    em
    0.84
    ak
    0.84
    im
    0.82
    ب
    0.82
    Activations Density 0.002%

    No Known Activations