© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 89723
    Prev
    Next
    INDEX
    Explanations

    demonstrative determiners in French

    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
     Бү
    0.70
     Etappe
    0.70
     Зу
    0.63
    licz
    0.61
    Су
    0.60
    Ни
    0.59
    恽
    0.59
    chi
    0.59
    CHICAGO
    0.59
    chnitten
    0.59
    POSITIVE LOGITS
     industri
    0.51
    यर
    0.50
     tena
    0.49
     i
    0.49
     he
    0.47
    𝐎
    0.47
     translator
    0.47
     لقد
    0.46
     WORK
    0.46
     Marriott
    0.46
    Activations Density 0.000%

    No Known Activations