© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 91344
    Prev
    Next
    INDEX
    Explanations

    French "je"

    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_11_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
    ,【
    0.70
     seçenek
    0.69
    ט
    0.67
     pelea
    0.65
    дентификаторы
    0.65
     تھا۔
    0.64
     பற்றிய
    0.64
     votar
    0.63
     preexisting
    0.62
     DISPLAYSURF
    0.62
    POSITIVE LOGITS
    pl
    0.63
    ell
    0.61
     namely
    0.60
    iquement
    0.60
     as
    0.59
    ynt
    0.59
    ace
    0.58
    9
    0.58
    ain
    0.57
    entes
    0.57
    Activations Density 0.000%

    No Known Activations