© 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. 30198
    Prev
    Next
    INDEX
    Explanations

    store

    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
    Not in Any Lists

    No Comments

    Negative Logits
    -
    0.36
     магазина
    0.36
     магазин
    0.34
     store
    0.34
     stores
    0.34
    ας
    0.34
    閉店
    0.33
     магази
    0.33
    kým
    0.32
     tiendas
    0.32
    POSITIVE LOGITS
    ل
    0.31
    لين
    0.31
    لها
    0.31
    لز
    0.30
     这
    0.30
    لية
    0.30
     Firearms
    0.28
    iere
    0.28
    ెస్
    0.28
    й
    0.28
    Activations Density 0.012%

    No Known Activations