© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142583
    Prev
    Next
    INDEX
    Explanations

    data preprocessing

    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_0_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
    t
    1.87
    و
    1.73
    ur
    1.56
    ak
    1.51
    st
    1.48
    f
    1.48
    ai
    1.45
    re
    1.45
    is
    1.44
    ه
    1.44
    POSITIVE LOGITS
     thời
    1.58
     zwią
    1.45
     giảm
    1.38
    ED
    1.30
     должности
    1.30
     pracę
    1.29
     coprodu
    1.28
     química
    1.27
     mục
    1.27
     académ
    1.26
    Activations Density 0.001%

    No Known Activations