© 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. 41346
    Prev
    Next
    INDEX
    Explanations

    code punctuation and keywords

    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
    }^{(\
    0.58
    ONEDB
    0.58
    ،
    0.57
    
    0.57
     او
    0.56
    Axes
    0.56
    PlistBuddy
    0.55
     lineColorSpace
    0.55
    или
    0.55
    tDBOutput
    0.55
    POSITIVE LOGITS
    MOST
    0.59
     I
    0.55
    '
    0.53
    łem
    0.52
    Ther
    0.52
     wonder
    0.50
     team
    0.49
     restroom
    0.49
    मंत्र
    0.49
    ami
    0.49
    Activations Density 0.017%

    No Known Activations