© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 204041
    Prev
    Next
    INDEX
    Explanations

    Chinese phrases

    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_56_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
     suficiente
    0.35
    檢
    0.35
    主な
    0.34
     शख
    0.34
    ณิต
    0.33
    笛
    0.33
     ま
    0.32
    يع
    0.32
    jumpa
    0.32
    在这种
    0.32
    POSITIVE LOGITS
    ³,
    0.39
    ohi
    0.37
     komt
    0.35
     alkalinity
    0.34
    }.${
    0.34
     ³
    0.34
     protests
    0.33
    和你
    0.33
    uwen
    0.33
     Рі
    0.32
    Activations Density 0.002%

    No Known Activations