© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 134527
    Prev
    Next
    INDEX
    Explanations

    viewport meta tag

    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_1_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
    )$;
    1.10
     zei
    1.02
     membre
    0.97
    বাবুর
    0.97
    ﻊ
    0.96
     chaque
    0.96
    )\\
    0.95
     κά
    0.93
    )}_{
    0.93
    :");
    0.93
    POSITIVE LOGITS
     is
    1.69
    ا
    1.44
    다
    1.43
    리
    1.43
    aj
    1.39
    ח
    1.28
    ా
    1.27
    re
    1.23
    ं
    1.22
    In
    1.21
    Activations Density 0.001%

    No Known Activations