© 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. 107552
    Prev
    Next
    INDEX
    Explanations

    c programming language or c++

    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
    c
    1.43
     a
    1.42
    ك
    1.37
    a
    1.27
     at
    1.24
     to
    1.22
     is
    1.17
    0
    1.16
    na
    1.13
    gg
    1.09
    POSITIVE LOGITS
    লে
    1.13
    지만
    1.04
    त
    1.01
    ри
    0.97
    ली
    0.93
    تهم
    0.91
    -
    0.91
    radiative
    0.90
    لوب
    0.89
    고
    0.88
    Activations Density 0.003%

    No Known Activations