© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 206587
    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_10_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
     व
    0.60
    <0x0D>
    0.57
     for
    0.56
     This
    0.54
     ও
    0.54
     以
    0.54
     ï
    0.54
     此
    0.54
     و
    0.52
     lý
    0.51
    POSITIVE LOGITS
    다면
    0.63
    此同时
    0.55
    顾
    0.55
    なっている
    0.54
    kan
    0.53
    dad
    0.53
     그다
    0.52
    ла
    0.51
    g
    0.50
    დან
    0.50
    Activations Density 0.000%

    No Known Activations