© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142165
    Prev
    Next
    INDEX
    Explanations

    Arabic, Vietnamese, Latin, Turkish 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_0_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
    T
    1.61
    W
    1.61
    R
    1.55
    I
    1.49
    もら
    1.45
    A
    1.39
    И
    1.39
    도
    1.38
    İ
    1.34
    Jeg
    1.33
    POSITIVE LOGITS
    and
    1.55
     be
    1.49
     to
    1.42
    ير
    1.30
     расположение
    1.26
    не
    1.20
    การ
    1.16
    ó
    1.13
     monstros
    1.12
    h
    1.12
    Activations Density 0.000%

    No Known Activations