© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214981
    Prev
    Next
    INDEX
    Explanations

    foreign language words

    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_5_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
     are
    0.79
    ب
    0.75
    ی
    0.61
    ations
    0.60
    are
    0.60
    ors
    0.58
    on
    0.58
    ы
    0.57
    ों
    0.55
    وں
    0.54
    POSITIVE LOGITS
    ד
    0.69
     দ্য
    0.53
     עד
    0.51
    ;
    0.51
    daki
    0.50
     něco
    0.50
     וי
    0.49
    ні
    0.49
    स
    0.48
     ollut
    0.47
    Activations Density 0.000%

    No Known Activations