© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 89995
    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_23_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
     შ
    0.49
    published
    0.48
    method
    0.47
    work
    0.46
    patent
    0.46
    such
    0.46
    longer
    0.46
    requ
    0.45
    rendering
    0.45
    collabor
    0.45
    POSITIVE LOGITS
    NCC
    0.57
    indelijk
    0.52
    ാൻഡ്
    0.50
    Ყ
    0.48
    гій
    0.48
    ява
    0.48
    দের
    0.47
    صحاب
    0.47
    цької
    0.46
    সাই
    0.46
    Activations Density 0.000%

    No Known Activations