© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 56818
    Prev
    Next
    INDEX
    Explanations

    limitless possibilities and resources

    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_11_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
    이었
    0.63
     aryl
    0.63
     ל
    0.61
     л
    0.61
     այ
    0.61
     tộc
    0.61
    噰
    0.60
     ل
    0.59
     ی
    0.59
     אחר
    0.59
    POSITIVE LOGITS
    as
    0.89
    et
    0.86
    ar
    0.80
    ad
    0.72
    0
    0.70
    in
    0.70
    Count
    0.68
    Field
    0.66
    a
    0.66
    art
    0.64
    Activations Density 0.003%

    No Known Activations