© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 40757
    Prev
    Next
    INDEX
    Explanations

    :

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    떄
    0.42
     moreover
    0.42
     scrape
    0.40
    ibaldi
    0.39
     david
    0.39
     précédent
    0.39
     previously
    0.39
     再
    0.39
     Dalib
    0.38
     sir
    0.38
    POSITIVE LOGITS
    ेंशन
    0.42
     Picchu
    0.41
     `$
    0.39
     '$
    0.36
    হা
    0.36
     दंग
    0.35
     ')[
    0.35
     `"
    0.35
     систе
    0.34
     "{{
    0.34
    Activations Density 0.000%

    No Known Activations