© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 207173
    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
    class
    0.52
    顔
    0.50
     micrograms
    0.47
    나
    0.47
    let
    0.46
    必要がある
    0.46
    後ろ
    0.45
    end
    0.43
    dice
    0.42
    を送
    0.42
    POSITIVE LOGITS
    捆
    0.55
     úpl
    0.52
     sympt
    0.50
     ബാറ്ററി
    0.50
     senere
    0.50
     équipé
    0.50
     enquanto
    0.48
     çekti
    0.48
    مدينة
    0.48
     simplement
    0.47
    Activations Density 0.000%

    No Known Activations