© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 238231
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis or code block end

    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_25_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
    íř
    0.39
    mgr
    0.38
     Messrs
    0.37
    ränkt
    0.37
    恁
    0.36
    寜
    0.36
    lerim
    0.36
     เอ่อ
    0.36
     全部
    0.34
     оригіналу
    0.34
    POSITIVE LOGITS
    CDS
    0.36
     mechanical
    0.36
     multi
    0.36
    وت
    0.36
    レ
    0.35
    かで
    0.35
    芻
    0.35
    简
    0.34
     phân
    0.34
     FACS
    0.34
    Activations Density 0.000%

    No Known Activations