© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 32921
    Prev
    Next
    INDEX
    Explanations

    list items

    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
    图
    0.77
    圖
    0.68
    図
    0.64
     图
    0.56
     diagram
    0.46
     圖
    0.46
     図
    0.46
    とは
    0.41
     diagrams
    0.40
    的那
    0.38
    POSITIVE LOGITS
    首
    0.39
    বৃত্ত
    0.38
    ক্ষণ
    0.38
    其
    0.38
    内容的
    0.37
    攥
    0.37
    列表中
    0.37
    多个
    0.36
    心中
    0.36
    这样一个
    0.36
    Activations Density 0.034%

    No Known Activations