© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130185
    Prev
    Next
    INDEX
    Explanations

    Estrategia, eighty, Epson

    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
    (
    1.47
     clic
    1.09
     σε
    1.03
     сервер
    1.03
     previewBuilder
    1.01
     signific
    0.96
     програм
    0.93
     rhino
    0.93
    (.*
    0.93
     resalt
    0.92
    POSITIVE LOGITS
    ون
    2.08
    다
    1.39
    ل
    1.37
    ש
    1.23
    to
    1.20
    j
    1.20
    و
    1.19
    ell
    1.18
    ان
    1.16
    ي
    1.09
    Activations Density 0.001%

    No Known Activations