© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 55019
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
    كذا
    0.41
    pairwise
    0.38
    腮
    0.38
    Suddenly
    0.37
     йөкләү
    0.37
    fla
    0.37
    opp
    0.36
     পারস্প
    0.36
    </footer>
    0.36
    ottam
    0.36
    POSITIVE LOGITS
     september
    0.59
     shakespeare
    0.57
     january
    0.56
     steve
    0.56
     october
    0.55
     african
    0.55
     charles
    0.55
     scottish
    0.55
     america
    0.54
     american
    0.54
    Activations Density 0.000%

    No Known Activations