© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 80500
    Prev
    Next
    INDEX
    Explanations

    :nth-child() selectors

    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_31_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
    리학
    0.43
    enschap
    0.40
    estructive
    0.39
    ()<<
    0.38
    착
    0.38
    Cntr
    0.38
    iedenis
    0.37
    叭
    0.36
     착
    0.36
    ურნ
    0.36
    POSITIVE LOGITS
    backend
    0.40
     respal
    0.36
     backend
    0.35
    リュ
    0.35
     Yuki
    0.35
    Backend
    0.35
    ोजना
    0.34
    ']],
    0.33
     cốt
    0.33
    เหล่านี้
    0.32
    Activations Density 0.000%

    No Known Activations