© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1042
    Prev
    Next
    INDEX
    Explanations

    is or was followed by adjective/participle

    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_39_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
     ★★
    0.16
     ppm
    0.15
     विरोध
    0.15
     লুকিয়ে
    0.15
     एच
    0.15
     লুকিয়ে
    0.15
     एनसी
    0.15
     zooms
    0.15
     (-
    0.14
    0.14
    POSITIVE LOGITS
    jarige
    0.17
    ichar
    0.16
     hasard
    0.16
    ρθ
    0.16
     sdf
    0.16
     contextual
    0.15
    DbContext
    0.15
    ర్యా
    0.15
     damned
    0.15
    oworld
    0.15
    Activations Density 0.763%

    No Known Activations