© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14491
    Prev
    Next
    INDEX
    Explanations

    French territories and overseas departments

    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_15_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
     フランス
    0.63
     н
    0.63
     Пари
    0.63
     Фран
    0.60
     *)$
    0.58
     n
    0.57
     rameaux
    0.57
     Франции
    0.56
     Frankreich
    0.55
     পারিত
    0.55
    POSITIVE LOGITS
    sb
    0.56
    骏
    0.51
    kh
    0.49
    stwo
    0.49
    schrift
    0.48
    স
    0.48
    ryption
    0.48
    स
    0.47
    vær
    0.47
    es
    0.47
    Activations Density 0.001%

    No Known Activations