© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 93419
    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_11_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
     ομά
    0.53
    Afghanistan
    0.51
    ӵ
    0.51
    Hudson
    0.50
     Atmosphäre
    0.48
     җиңү
    0.48
    Established
    0.47
    Constitution
    0.47
     Kinn
    0.47
    History
    0.47
    POSITIVE LOGITS
    𝓮
    0.52
    ิศ
    0.49
    ibh
    0.48
    iza
    0.45
    िकी
    0.44
    ิค
    0.43
     กู
    0.43
    aric
    0.43
     শুক
    0.43
     manifi
    0.43
    Activations Density 0.000%

    No Known Activations