© 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. 51746
    Prev
    Next
    INDEX
    Explanations

    Toronto

    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
     Andaman
    0.70
     padr
    0.59
    pson
    0.55
     Kauai
    0.55
    ẳ
    0.55
     Guam
    0.55
     کوردستان
    0.55
     সেটা
    0.52
    nolds
    0.52
    rtimes
    0.52
    POSITIVE LOGITS
    Toronto
    0.91
     Toronto
    0.79
    v
    0.76
    f
    0.69
    Chicago
    0.63
    g
    0.63
    d
    0.62
    어
    0.62
    kowe
    0.61
    Ontario
    0.60
    Activations Density 0.011%

    No Known Activations