© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 160907
    Prev
    Next
    INDEX
    Explanations

    uisng, uib, ui

    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_2_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
     be
    1.52
    ט
    1.18
     are
    1.09
    ס
    0.99
    ได้
    0.99
    ส่ง
    0.94
    斯的
    0.94
    มี
    0.91
     as
    0.90
     styl
    0.89
    POSITIVE LOGITS
    ا
    1.34
    ib
    1.32
    a
    1.23
    '
    1.19
    ri
    1.16
    ور
    1.09
    and
    1.09
    ні
    1.06
    но
    1.04
    ни
    1.04
    Activations Density 0.000%

    No Known Activations