© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 19647
    Prev
    Next
    INDEX
    Explanations

    Facebook Messenger

    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_15_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
     honoring
    0.33
    %
    0.32
     nunca
    0.31
    Đây
    0.30
    </h6>
    0.29
    <h2>
    0.29
     IMPORTANT
    0.29
    POT
    0.29
     Teenage
    0.29
    ưng
    0.28
    POSITIVE LOGITS
     ս
    0.33
    *}\
    0.30
    îtier
    0.30
     ка
    0.30
     المكان
    0.30
     заб
    0.29
    videos
    0.28
     смартфо
    0.28
     Ellsworth
    0.28
    propagation
    0.27
    Activations Density 0.004%

    No Known Activations