© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 105778
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and equations

    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
    1.37
    ط
    1.31
     for
    1.30
    리
    1.20
    i
    1.08
     in
    1.03
    ி
    1.03
     is
    1.02
     at
    1.00
    ก
    0.99
    POSITIVE LOGITS
    $,
    1.06
    ap
    1.05
    ing
    1.01
    ov
    0.94
    \",
    0.91
    ,\\
    0.89
    have
    0.86
    니다
    0.85
    -,
    0.84
    ;",
    0.84
    Activations Density 0.001%

    No Known Activations