© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 121603
    Prev
    Next
    INDEX
    Explanations

    codes and numbers

    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_27_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
    PT
    0.31
    Philosophy
    0.30
    IAS
    0.30
    期待
    0.29
    intre
    0.29
    Profiling
    0.29
    Profil
    0.29
    )}$,
    0.29
    ึ
    0.29
     भग्न
    0.29
    POSITIVE LOGITS
     nueva
    0.37
     new
    0.34
     NCAA
    0.34
     averaging
    0.34
     vapor
    0.34
     Vapor
    0.33
     fair
    0.33
     overseas
    0.33
     retailers
    0.33
     newer
    0.33
    Activations Density 0.000%

    No Known Activations