© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10882
    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_13_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
     territor
    0.50
    ritte
    0.49
     brighter
    0.48
     −
    0.48
     ப
    0.48
     פ
    0.48
     np
    0.47
     competit
    0.47
     т
    0.47
     τ
    0.46
    POSITIVE LOGITS
     Prony
    0.65
     Duane
    0.61
    ﮕ
    0.56
     стиле
    0.54
     gosto
    0.53
    ProjectReference
    0.53
    ګه
    0.53
    гото
    0.52
    \%),
    0.52
     Downey
    0.52
    Activations Density 0.000%

    No Known Activations