© 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. 210137
    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
    はじめ
    0.57
     sélection
    0.55
    皚
    0.52
    選択
    0.51
     જણાવ
    0.51
    チャレンジ
    0.50
    ডিস
    0.49
     решать
    0.49
     décidé
    0.49
     mérite
    0.49
    POSITIVE LOGITS
    </b>
    0.44
    ARE
    0.43
    ‬‬
    0.43
    àn
    0.43
    تبر
    0.43
    GetUser
    0.41
    ete
    0.41
    uter
    0.41
    MANN
    0.41
     regolare
    0.41
    Activations Density 0.000%

    No Known Activations