© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14348
    Prev
    Next
    INDEX
    Explanations

    stroke width solid 3

    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_40_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
     thin
    2.41
     Thin
    2.14
    Thin
    2.14
     thinner
    2.05
    thin
    2.03
    薄
    2.03
     thick
    1.88
     thicker
    1.82
    厚
    1.81
    thick
    1.75
    POSITIVE LOGITS
    欱
    0.41
     Drav
    0.37
    BleStatus
    0.37
     Fid
    0.37
    mler
    0.36
     Precipitation
    0.36
     boute
    0.36
     Wikip
    0.35
     Encyclop
    0.35
     Rabb
    0.35
    Activations Density 0.050%

    No Known Activations