© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34826
    Prev
    Next
    INDEX
    Explanations

    listing items or points

    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
    i
    0.85
     auffi
    0.79
    kannya
    0.78
    removeChild
    0.77
    ל
    0.77
    のは
    0.73
    kowej
    0.71
    T
    0.69
    ваны
    0.68
    י
    0.68
    POSITIVE LOGITS
    ج
    0.85
    اف
    0.79
    ف
    0.77
    s
    0.74
    ž
    0.71
    \
    0.71
    ickers
    0.70
     as
    0.69
    ים
    0.67
    да
    0.66
    Activations Density 0.001%

    No Known Activations