© 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. 205609
    Prev
    Next
    INDEX
    Explanations

    number, count, or limit

    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
     HTTPS
    0.25
     utan
    0.23
     بع
    0.23
     עם
    0.23
    ారి
    0.23
    জার
    0.22
    قبال
    0.22
    isać
    0.22
     ב
    0.22
    Avec
    0.21
    POSITIVE LOGITS
     veto
    0.30
    leneck
    0.28
    culture
    0.25
    केंद्र
    0.24
    nt
    0.24
     urge
    0.24
     encouraging
    0.24
     Valverde
    0.24
    4
    0.23
     pourrait
    0.23
    Activations Density 0.007%

    No Known Activations