© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 29557
    Prev
    Next
    INDEX
    Explanations

    server.js, config, controllers

    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
    漕
    0.34
    Django
    0.32
    ренко
    0.32
     undis
    0.31
    人物
    0.31
    /<
    0.31
    参考
    0.31
     parfaitement
    0.30
     mimicking
    0.30
    четов
    0.30
    POSITIVE LOGITS
    Conte
    0.38
     PSD
    0.37
    ቿ
    0.36
    yank
    0.36
     weit
    0.35
    keen
    0.35
     여기에
    0.35
     век
    0.34
    PSD
    0.34
     initiated
    0.34
    Activations Density 0.002%

    No Known Activations