© 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. 40588
    Prev
    Next
    INDEX
    Explanations

    asking questions

    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
     നേരി
    0.37
    chus
    0.36
    혀
    0.35
    clos
    0.34
     Pole
    0.34
     dạ
    0.34
    Pole
    0.34
     Ocho
    0.34
    ictionary
    0.33
     siguiente
    0.33
    POSITIVE LOGITS
     streng
    0.37
    maxcdn
    0.36
     rave
    0.36
     review
    0.36
    Review
    0.36
     Review
    0.35
     모양
    0.35
    垢
    0.35
     advised
    0.34
     Reprint
    0.34
    Activations Density 0.006%

    No Known Activations