© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 94137
    Prev
    Next
    INDEX
    Explanations

    information structure

    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_60_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
     CtApp
    0.18
    ार्टम
    0.17
    <unused1855>
    0.17
    |");
    0.17
     SupCt
    0.17
     comienza
    0.17
     comenzar
    0.17
    AYA
    0.17
     siphon
    0.17
    एसएल
    0.17
    POSITIVE LOGITS
     A
    0.21
    order
    0.18
    form
    0.18
    post
    0.15
     F
    0.15
    class
    0.15
    met
    0.15
    term
    0.15
    <em>
    0.15
    find
    0.15
    Activations Density 0.001%

    No Known Activations