© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 81945
    Prev
    Next
    INDEX
    Explanations

    kind of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_29_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
     só
    0.36
     사용하는
    0.35
    ↵
    0.35
     Enzymes
    0.33
    币
    0.33
     UX
    0.33
     Quest
    0.32
     pued
    0.32
     zdję
    0.32
     Xcode
    0.32
    POSITIVE LOGITS
    靂
    0.43
    ಾಯಿತು
    0.39
     Lichten
    0.36
     measles
    0.36
    ruz
    0.35
     కారణంగా
    0.34
     ഉള്‍
    0.34
     தொற்று
    0.34
     জবাবে
    0.33
    保護
    0.32
    Activations Density 0.005%

    No Known Activations