© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49098
    Prev
    Next
    INDEX
    Explanations

    Japanese language

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
    救
    0.44
    টিউ
    0.40
    梯
    0.39
    CLUDING
    0.38
    催
    0.37
    commend
    0.37
    glfw
    0.36
    똘
    0.36
    irá
    0.36
    fq
    0.36
    POSITIVE LOGITS
    닐
    0.43
     습
    0.40
    जी
    0.40
    Dart
    0.40
     dart
    0.39
     Indy
    0.38
     Hempstead
    0.38
     Suk
    0.37
     Repl
    0.37
     Spann
    0.37
    Activations Density 0.002%

    No Known Activations