© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 146365
    Prev
    Next
    INDEX
    Explanations

    Chinese 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_59_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
    $~
    0.46
     杯
    0.46
     he
    0.46
     云
    0.45
    erved
    0.43
     界
    0.42
     Vigil
    0.42
     Coalition
    0.42
     Attic
    0.41
     忄
    0.41
    POSITIVE LOGITS
     And
    0.65
     To
    0.52
     We
    0.49
    And
    0.47
    表
    0.46
     By
    0.44
    金
    0.43
     It
    0.43
    نة
    0.41
    νη
    0.41
    Activations Density 0.007%

    No Known Activations