© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 131382
    Prev
    Next
    INDEX
    Explanations

    . INC

    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
     can
    1.25
    de
    1.23
    ce
    1.20
    >
    1.19
    ية
    1.18
    '
    1.18
    س
    1.16
    -
    1.13
    ва
    1.13
    ：
    1.12
    POSITIVE LOGITS
     Ř
    1.08
     Polres
    1.00
     Sử
    0.99
     Слова
    0.96
     Chỉ
    0.96
     Nếu
    0.95
     Cái
    0.95
     ﺍ
    0.94
     Ска
    0.93
     Điều
    0.92
    Activations Density 0.001%

    No Known Activations