© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 45874
    Prev
    Next
    INDEX
    Explanations

    published, invest, Number, Video, Script

    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_10_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
    م
    0.29
    ক
    0.29
    ب
    0.28
    A
    0.28
     A
    0.28
    м
    0.27
     año
    0.27
    ve
    0.27
    로
    0.26
    on
    0.26
    POSITIVE LOGITS
    मिका
    0.28
    '
    0.27
    imming
    0.26
     මහ
    0.25
    ening
    0.25
    喜欢的
    0.24
     گفت
    0.24
     చేసే
    0.23
     musik
    0.23
    ộng
    0.23
    Activations Density 0.012%

    No Known Activations