© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 41171
    Prev
    Next
    INDEX
    Explanations

    python import from collections

    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
    Negative Logits
    icing
    0.66
    ti
    0.61
     so
    0.60
    nl
    0.59
    imacy
    0.59
    k
    0.59
    state
    0.57
    nan
    0.56
    int
    0.55
    ff
    0.54
    POSITIVE LOGITS
    リーダー
    0.55
    ੱਕ
    0.54
    А
    0.53
     miércoles
    0.52
    オンライン
    0.52
    ଆ
    0.50
     пользователи
    0.49
    ონი
    0.49
     गुरूवार
    0.49
    اری
    0.48
    Activations Density 0.002%

    No Known Activations