© 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. 24942
    Prev
    Next
    INDEX
    Explanations

    only / és

    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
    :
    1.07
    '
    1.03
    ;
    1.00
    c
    0.84
    ’
    0.82
    し
    0.80
    g
    0.71
    ದ
    0.70
     attuale
    0.70
    H
    0.70
    POSITIVE LOGITS
     for
    0.95
    for
    0.88
    at
    0.88
    as
    0.84
    ncoder
    0.80
    qués
    0.76
    ním
    0.75
    asen
    0.74
    ong
    0.73
     ر
    0.73
    Activations Density 0.003%

    No Known Activations