© 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. 45244
    Prev
    Next
    INDEX
    Explanations

    quarterback, touchdowns, QBs

    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
    ٤
    0.58
    ش
    0.57
     баскетбол
    0.56
    ۳
    0.56
     سهل
    0.55
     автомобиль
    0.53
     سبيل
    0.52
    8
    0.52
     deportivas
    0.51
    ف
    0.51
    POSITIVE LOGITS
    n
    0.85
    NER
    0.83
    NN
    0.73
    nate
    0.73
    DA
    0.71
    S
    0.70
    M
    0.70
    TER
    0.68
    තුව
    0.65
    nél
    0.65
    Activations Density 0.000%

    No Known Activations