© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 105865
    Prev
    Next
    INDEX
    Explanations

    partic. particulièrement, parti pris

    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
    لي
    1.40
     to
    1.09
    ли
    1.08
     a
    1.02
    يد
    1.01
     antics
    1.01
    اری
    0.99
    のみ
    0.99
    お手
    0.95
    ატ
    0.95
    POSITIVE LOGITS
    ों
    1.52
    s
    1.33
    س
    1.30
    ก
    1.26
    the
    1.23
    માં
    1.15
    sthe
    1.13
    st
    1.07
    sa
    1.07
    :
    1.04
    Activations Density 0.001%

    No Known Activations