© 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. 50110
    Prev
    Next
    INDEX
    Explanations

    build commands

    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
    logback
    0.40
     搭
    0.39
    ommen
    0.39
    wach
    0.39
     Reserve
    0.38
     বোঝার
    0.38
    PAS
    0.38
     weaves
    0.38
    requ
    0.38
    hess
    0.37
    POSITIVE LOGITS
    WithOptions
    0.42
     ..."
    0.41
     _;
    0.40
     uninstall
    0.38
     unlock
    0.37
     fclose
    0.37
     желательно
    0.37
    ..."
    0.37
     Suitable
    0.37
    インスト
    0.37
    Activations Density 0.000%

    No Known Activations