© 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. 29619
    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
     עי
    0.52
     formatting
    0.46
    чном
    0.46
     生成
    0.44
     reda
    0.44
     检测
    0.44
    ج
    0.44
     ü
    0.43
     Design
    0.42
     Brief
    0.42
    POSITIVE LOGITS
     conhecimento
    0.50
    nrB
    0.50
    삿
    0.48
    ᱗
    0.48
    ၇
    0.47
    換え
    0.47
     অনুয
    0.47
    renowned
    0.47
    Enfin
    0.47
     happened
    0.47
    Activations Density 0.000%

    No Known Activations