© 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. 25442
    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
    in
    0.55
    the
    0.47
    infer
    0.43
    心中的
    0.42
    Bahn
    0.42
    рын
    0.42
    вах
    0.41
    诹
    0.41
    ્સ
    0.41
    الوج
    0.40
    POSITIVE LOGITS
     डिफरेंट
    0.54
     przyczyn
    0.54
     entraî
    0.53
    モチ
    0.52
     pozwoli
    0.52
     opérations
    0.51
     różnych
    0.49
    nitř
    0.48
     sytuacji
    0.48
     prévoit
    0.48
    Activations Density 0.000%

    No Known Activations