© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 28590
    Prev
    Next
    INDEX
    Explanations

    East asian topics, names, and organizations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
    vah
    0.43
     tins
    0.40
    ਹ
    0.39
     Nawaz
    0.38
    oxymethyl
    0.38
     alphabetically
    0.37
     مصنوعی
    0.37
     भोपाल
    0.37
     అలీ
    0.37
    Hindu
    0.36
    POSITIVE LOGITS
     Cantonese
    0.50
    ≧
    0.50
    
    0.48
     Chongqing
    0.47
    －
    0.47
    ｜
    0.46
    ．
    0.45
    ＝
    0.45
    ﹒
    0.43
     Mongolian
    0.42
    Activations Density 0.015%

    No Known Activations