© 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. 41022
    Prev
    Next
    INDEX
    Explanations

    theorized

    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
    (
    1.00
    3
    0.94
    -
    0.90
    تان
    0.79
    ()
    0.69
    5
    0.68
    4
    0.68
    +
    0.67
    ([])
    0.64
    9
    0.64
    POSITIVE LOGITS
     teorías
    0.78
     teórico
    0.76
     teoría
    0.71
     is
    0.71
    理論
    0.65
     thị
    0.63
     theoretically
    0.63
    理论
    0.63
     теории
    0.62
     in
    0.61
    Activations Density 0.001%

    No Known Activations