© 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. 31391
    Prev
    Next
    INDEX
    Explanations

    technical accuracy

    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
    WeekDates
    0.42
     وك
    0.42
    xcol
    0.40
    ಗಳಿವೆ
    0.40
    ༠
    0.39
     moduleId
    0.39
     বাস্তবায়
    0.39
    xcodep
    0.38
     مختلفة
    0.38
    ༡
    0.38
    POSITIVE LOGITS
     invited
    0.38
    Te
    0.38
    ்ப்ப
    0.37
    png
    0.37
    di
    0.35
    errno
    0.35
    thing
    0.35
    mingw
    0.34
    情
    0.34
    дим
    0.34
    Activations Density 0.000%

    No Known Activations