© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173985
    Prev
    Next
    INDEX
    Explanations

    profile account page

    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_20_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
     rencontr
    0.57
     Flüss
    0.51
    pèce
    0.50
     Благодаря
    0.48
    是你
    0.48
     ফ্রান্স
    0.48
    𝐲
    0.47
     Choisissez
    0.46
     oWord
    0.46
     Шрифт
    0.46
    POSITIVE LOGITS
     corner
    0.47
     corners
    0.47
     rever
    0.44
    OR
    0.42
    由
    0.41
    idados
    0.41
     simultaneously
    0.40
    lica
    0.40
    ोध
    0.40
     ongoing
    0.39
    Activations Density 0.000%

    No Known Activations