© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31223
    Prev
    Next
    INDEX
    Explanations

    Zhong

    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_50_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
    Tan
    0.89
     Tan
    0.87
     TAN
    0.84
    TAN
    0.82
    谭
    0.78
    tan
    0.77
     tan
    0.75
    譚
    0.75
    탄
    0.72
     탄
    0.68
    POSITIVE LOGITS
     Zhong
    0.86
    zhong
    0.79
    锺
    0.78
    鍾
    0.74
    종
    0.71
     zhong
    0.71
    种
    0.70
    種
    0.70
    중
    0.66
    钟
    0.66
    Activations Density 0.019%

    No Known Activations