© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57364
    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_11_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
    tains
    0.49
    Solutions
    0.47
    лению
    0.46
    )。
    0.46
    ){
    0.44
    OT
    0.43
    +
    0.43
    imuth
    0.43
    Cell
    0.42
    Center
    0.42
    POSITIVE LOGITS
    🅐
    0.54
     incest
    0.53
     προ
    0.52
     pecans
    0.52
     adolescents
    0.50
     donors
    0.49
    观念
    0.48
     bullies
    0.48
     vampires
    0.48
     дітей
    0.47
    Activations Density 0.000%

    No Known Activations