© 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. 108926
    Prev
    Next
    INDEX
    Explanations

    下降，修，刻，祭，压

    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
    ي
    1.61
    لي
    1.21
    ми
    1.18
    드
    1.09
    ে
    1.04
    স
    0.98
    י
    0.97
    ↵
    0.96
    ো
    0.94
    스는
    0.89
    POSITIVE LOGITS
    ing
    1.77
    .
    1.64
    0
    1.61
    k
    1.39
    !
    1.38
    ado
    1.37
     on
    1.34
    yl
    1.23
    ?
    1.23
    we
    1.19
    Activations Density 0.000%

    No Known Activations