© 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. 34920
    Prev
    Next
    INDEX
    Explanations

    p-value, indicating statistical significance

    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
    </h3>
    1.04
    ↵
    1.02
     a
    0.93
    </h2>
    0.91
     an
    0.84
    </h4>
    0.84
     I
    0.79
     what
    0.79
    r
    0.76
    ।
    0.76
    POSITIVE LOGITS
    ست
    0.73
    보는
    0.67
    あり
    0.66
    یتی
    0.65
    ስቃ
    0.65
    𝙥
    0.65
    parsedBlock
    0.64
    thinmathspace
    0.64
    |>
    0.62
    보
    0.62
    Activations Density 0.002%

    No Known Activations