© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 129580
    Prev
    Next
    INDEX
    Explanations

    кон

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    Classpath
    0.39
    olina
    0.36
     disposizione
    0.35
     przeciw
    0.35
    apin
    0.35
     вс
    0.34
    shel
    0.34
     disposing
    0.34
     shepherd
    0.33
    짐
    0.33
    POSITIVE LOGITS
     кон
    2.11
     컨
    1.63
    コン
    1.60
    คอน
    1.53
     kon
    1.52
     CON
    1.48
     কন
    1.47
    컨
    1.47
     Кон
    1.45
     コン
    1.45
    Activations Density 0.001%

    No Known Activations