© 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. 127149
    Prev
    Next
    INDEX
    Explanations

    over-smoothing, over-extraction, overgeneralization

    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
    ين
    0.87
    の名
    0.80
    is
    0.79
    يل
    0.79
    لي
    0.77
    ის
    0.76
    他
    0.73
    את
    0.69
    اي
    0.68
    لم
    0.66
    POSITIVE LOGITS
     in
    0.89
    r
    0.79
    '
    0.79
    y
    0.77
    "
    0.75
    pathetic
    0.67
    gen
    0.66
    I
    0.64
    IFF
    0.63
    grip
    0.62
    Activations Density 0.002%

    No Known Activations