© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159913
    Prev
    Next
    INDEX
    Explanations

    second most abundant

    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_2_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
    ق
    1.73
    স
    1.57
    ك
    1.52
    ת
    1.39
    ل
    1.36
    ла
    1.34
    s
    1.28
    st
    1.27
    ع
    1.24
    us
    1.22
    POSITIVE LOGITS
    U
    1.17
     on
    1.04
    ᱶ
    1.01
     rivulet
    1.00
    ೇವಿನ
    0.97
    燹
    0.96
    UIC
    0.95
     Бүгенге
    0.95
     ﺍ
    0.95
     pudi
    0.93
    Activations Density 0.000%

    No Known Activations