© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144035
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     സ്ഥാന
    0.61
     بقي
    0.59
    カ
    0.57
     މަ
    0.57
    。",
    0.55
    γμα
    0.55
    偉
    0.55
     gestion
    0.55
     continuer
    0.55
    ですか
    0.54
    POSITIVE LOGITS
    FIT
    0.57
    h
    0.55
     Studies
    0.54
     H
    0.54
     Apps
    0.53
     Guests
    0.53
     Developments
    0.53
     Et
    0.52
     Wellness
    0.52
     Agents
    0.51
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.