© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130573
    Prev
    Next
    INDEX
    Explanations

    foreign characters and symbols

    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_1_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
    近い
    1.26
    یا
    1.19
    لیل
    1.16
    ری
    1.16
     Очень
    1.08
    ﺏ
    1.08
     jednego
    1.07
    ﺵ
    1.06
     Якщо
    1.05
    IA
    1.04
    POSITIVE LOGITS
     be
    1.63
     of
    1.39
     in
    1.36
    in
    1.34
    :
    1.34
    i
    1.30
    ه
    1.30
    a
    1.26
    \
    1.21
    (
    1.18
    Activations Density 0.000%

    No Known Activations