© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 102640
    Prev
    Next
    INDEX
    Explanations

    "commercially" or "out there"

    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_14_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    za
    0.23
    ską
    0.23
     دنی
    0.22
     Citt
    0.22
    Worlds
    0.22
    લ
    0.22
    zell
    0.22
    မြို့
    0.21
    Variant
    0.21
    ästä
    0.21
    POSITIVE LOGITS
     aplicativo
    0.21
     were
    0.20
     año
    0.20
    '));
    0.20
     qued
    0.20
     alguna
    0.19
     setInterval
    0.19
     mensagem
    0.19
     agrup
    0.19
     jederzeit
    0.19
    Activations Density 0.002%

    No Known Activations