© 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. 29243
    Prev
    Next
    INDEX
    Explanations

    dump

    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
    する
    0.36
    2
    0.35
    3
    0.35
     be
    0.34
    4
    0.34
    时
    0.32
    </u>
    0.31
    時
    0.31
    P
    0.30
    ，“
    0.29
    POSITIVE LOGITS
    ون
    0.37
    ра
    0.29
     endings
    0.28
    fh
    0.27
    uo
    0.27
    getPrototypeOf
    0.27
    uas
    0.27
    -(
    0.26
    ir
    0.26
    inand
    0.26
    Activations Density 0.002%

    No Known Activations