© 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. 50680
    Prev
    Next
    INDEX
    Explanations

    heading

    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
    n
    1.13
    re
    0.72
    escol
    0.72
    bindingFields
    0.71
    es
    0.70
    ikos
    0.69
    niji
    0.68
    esinin
    0.63
    header
    0.63
     Δεν
    0.63
    POSITIVE LOGITS
    .
    0.95
    ק
    0.91
    ک
    0.84
    -
    0.84
    স
    0.81
    я
    0.79
    ที่
    0.79
    ห
    0.77
    ہ
    0.76
    ни
    0.75
    Activations Density 0.005%

    No Known Activations