© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 211888
    Prev
    Next
    INDEX
    Explanations

    please

    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_20_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
     З
    0.34
     realiz
    0.34
    بعة
    0.33
     bearish
    0.32
     mirip
    0.32
    γγελμα
    0.32
    lonitrile
    0.31
    mitted
    0.31
    hammad
    0.31
    缕
    0.31
    POSITIVE LOGITS
    utte
    0.36
    autres
    0.32
    rata
    0.30
    per
    0.29
     recyclable
    0.29
    rater
    0.28
    \,\
    0.27
    #,
    0.27
    icits
    0.27
    essere
    0.27
    Activations Density 0.001%

    No Known Activations