© 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. 35878
    Prev
    Next
    INDEX
    Explanations

    foreign language grammatical particles

    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
    ？
    0.59
     že
    0.57
    brella
    0.55
     marít
    0.53
     Shipbuilding
    0.52
    ভিশ
    0.51
     biscuits
    0.51
    ano
    0.50
     obraz
    0.50
     zako
    0.50
    POSITIVE LOGITS
    a
    0.93
    ه
    0.76
    ה
    0.66
    ی
    0.65
    া
    0.61
    의
    0.60
    ій
    0.58
    ي
    0.58
    ID
    0.57
    ા
    0.56
    Activations Density 0.001%

    No Known Activations