© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 46335
    Prev
    Next
    INDEX
    Explanations

    public class definitions

    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_22_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
     মানুষ
    0.30
     Mining
    0.29
    лії
    0.29
     ల
    0.28
     Menschen
    0.28
     শর্
    0.27
    IRON
    0.27
    びに
    0.27
     أق
    0.27
     لوبی
    0.27
    POSITIVE LOGITS
     precum
    0.37
     coste
    0.36
    <b>
    0.35
     postura
    0.35
     acest
    0.33
    Richard
    0.33
     রহমানের
    0.32
     tooltip
    0.32
     brushing
    0.32
    本作
    0.32
    Activations Density 0.001%

    No Known Activations