© 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. 197341
    Prev
    Next
    INDEX
    Explanations

    OOP concepts

    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
     ശക്ത
    0.40
     passeio
    0.37
     Maximilian
    0.36
    ₎
    0.36
    логов
    0.35
     unidos
    0.35
     শক্তিশালী
    0.35
    .):
    0.35
     있게
    0.35
    遢
    0.35
    POSITIVE LOGITS
    MouseEvent
    0.44
    ColorLegend
    0.38
    দেশের
    0.38
    ahanam
    0.38
     xScale
    0.37
     Wisdom
    0.37
     Laugh
    0.37
     Cricket
    0.36
    전자
    0.36
    UTHERN
    0.36
    Activations Density 0.002%

    No Known Activations