© 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. 126882
    Prev
    Next
    INDEX
    Explanations

    Calment, Khan, Richter, filters

    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
    v
    0.88
    \
    0.78
    ש
    0.72
     \
    0.68
    한
    0.66
    b
    0.66
     Bonjour
    0.64
     Brav
    0.64
    ileg
    0.64
    ال
    0.63
    POSITIVE LOGITS
    та
    0.93
    с
    0.85
    า
    0.73
    oną
    0.71
     toa
    0.68
    த்தில்
    0.67
    ată
    0.67
     функций
    0.66
    ༧
    0.66
    Ϭ
    0.66
    Activations Density 0.000%

    No Known Activations