© 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. 31888
    Prev
    Next
    INDEX
    Explanations

    specific names

    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
     Letting
    0.40
    iejsc
    0.38
    륵
    0.37
    actyl
    0.37
    Ripple
    0.37
    Rated
    0.36
     Rye
    0.36
    ेंटल
    0.36
     Ripple
    0.36
    вається
    0.36
    POSITIVE LOGITS
     Mori
    0.39
    服务器
    0.38
     Mari
    0.38
     clone
    0.38
     cater
    0.38
    丽
    0.37
    瓴
    0.36
     Clifton
    0.36
    Statistics
    0.36
    ບໍ
    0.36
    Activations Density 0.003%

    No Known Activations