© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1004
    Prev
    Next
    INDEX
    Explanations

    list operations and data structures

    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_39_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
     बुल
    0.40
    graphHead
    0.40
     vit
    0.39
     submitting
    0.39
     waitUntil
    0.38
    ستا
    0.37
     Gerardo
    0.36
    郴
    0.36
     झुक
    0.35
     seclusion
    0.35
    POSITIVE LOGITS
    list
    0.42
    Measurement
    0.39
    Beer
    0.35
    lista
    0.35
     list
    0.35
     prices
    0.35
     Fil
    0.35
    Select
    0.35
    ListOf
    0.34
    Currency
    0.34
    Activations Density 0.065%

    No Known Activations