© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34231
    Prev
    Next
    INDEX
    Explanations

    pulchritudinous, PUCCH, PUSCH, Poiseuille

    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_3_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
    1.13
     (
    0.85
    ar
    0.82
    ה
    0.80
    고
    0.76
    l
    0.74
    ery
    0.70
    し
    0.69
    ר
    0.69
    '
    0.68
    POSITIVE LOGITS
     _:
    0.62
    நபியே
    0.61
    _:
    0.61
    _;
    0.61
    ية
    0.59
    的的
    0.59
    RIO
    0.59
     الزمن
    0.58
    <0x91>
    0.57
    ）,
    0.57
    Activations Density 0.002%

    No Known Activations