© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84267
    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_0_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
     Unusual
    0.57
    in
    0.54
     Intermediate
    0.52
     Notice
    0.52
     ae
    0.52
     Safe
    0.50
     Decoration
    0.49
     H
    0.49
     Special
    0.48
     Orientation
    0.48
    POSITIVE LOGITS
    карбо
    0.53
    мі
    0.52
    ология
    0.52
    норий
    0.50
    μένα
    0.49
    ڽ
    0.49
     университе
    0.48
    лянчук
    0.48
    masht
    0.47
    метр
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.