© 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. 34943
    Prev
    Next
    INDEX
    Explanations

    code punctuation and symbols

    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
    a
    0.64
    esk
    0.52
     keyed
    0.50
    ه
    0.49
            
    0.47
    keyed
    0.46
     `'\\
    0.46
     of
    0.44
    юще
    0.44
    padded
    0.43
    POSITIVE LOGITS
    .?
    0.51
    AddTime
    0.51
    .!
    0.50
     Taking
    0.46
    WORK
    0.45
    ,?
    0.45
    겅
    0.45
    ន
    0.45
    APK
    0.44
    .&
    0.44
    Activations Density 0.043%

    No Known Activations