© 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. 34998
    Prev
    Next
    INDEX
    Explanations

    Western Europe

    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
     Russian
    0.61
     ruso
    0.57
     Belarusian
    0.55
     Rusia
    0.54
     Beograd
    0.54
     duro
    0.54
     Ukrainian
    0.53
     ^{-
    0.52
    ня
    0.52
     러시아
    0.51
    POSITIVE LOGITS
    ７
    0.61
    เวล
    0.61
    ８
    0.55
     ourselves
    0.53
    Ｌ
    0.52
     heard
    0.50
     visualized
    0.50
     recompens
    0.50
    เวลา
    0.50
    Ｃ
    0.50
    Activations Density 0.019%

    No Known Activations