© 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. 41151
    Prev
    Next
    INDEX
    Explanations

    show, don't tell

    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
    usses
    0.56
    アンド
    0.56
    nieuw
    0.54
    新しい
    0.53
     agricultura
    0.53
    唇
    0.53
    ﺘ
    0.53
    णी
    0.52
    崽
    0.52
    ارب
    0.51
    POSITIVE LOGITS
     directive
    0.55
     mó
    0.55
     Directive
    0.54
     oder
    0.50
     malaria
    0.49
     series
    0.49
    '
    0.48
    ›
    0.48
     fors
    0.48
    ’
    0.48
    Activations Density 0.001%

    No Known Activations