© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 226762
    Prev
    Next
    INDEX
    Explanations

    checking in luggage or parking car

    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
    Negative Logits
    '
    0.99
    ;
    0.86
    S
    0.85
    I
    0.83
    .
    0.81
     et
    0.80
    H
    0.75
     .
    0.75
    ↵
    0.74
    volution
    0.73
    POSITIVE LOGITS
    л
    0.88
    abhuto
    0.82
     decisões
    0.80
     கெல்வின்
    0.79
     respostas
    0.79
     영역
    0.77
     вопросы
    0.77
     principais
    0.76
     домаћин
    0.76
     городской
    0.75
    Activations Density 0.011%

    No Known Activations