© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 57610
    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_59_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
    LOLL
    0.52
    🫠
    0.42
    !".
    0.41
    Auto
    0.41
    !!!");
    0.40
    OREM
    0.40
    !!"
    0.40
    !!");
    0.40
    oppable
    0.39
    !";
    0.39
    POSITIVE LOGITS
     setting
    0.42
     p
    0.40
     Heads
    0.40
     Setting
    0.39
    設定
    0.37
     rites
    0.37
     cost
    0.36
     heads
    0.35
     crater
    0.35
     st
    0.34
    Activations Density 0.000%

    No Known Activations