© 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. 102903
    Prev
    Next
    INDEX
    Explanations

    game genres or developer names

    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
    Negative Logits
     Р
    0.55
     С
    0.54
    ים
    0.52
     ,
    0.49
    ה
    0.48
     ・
    0.48
     Population
    0.48
    Ь
    0.48
     *
    0.47
     -
    0.47
    POSITIVE LOGITS
    amerikanischer
    0.43
     shutdowns
    0.43
    Commande
    0.43
    iciones
    0.43
     erreurs
    0.43
     famoso
    0.42
     wirtschaft
    0.42
    Phr
    0.42
    ството
    0.42
    喜剧
    0.42
    Activations Density 0.014%

    No Known Activations