© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 202824
    Prev
    Next
    INDEX
    Explanations

    integer programming

    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_6_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
    ۔
    1.15
     হাসপাত
    0.88
     در
    0.87
    ästä
    0.82
     whatnot
    0.79
    لام
    0.78
    ።
    0.78
     urethra
    0.77
    ។
    0.76
    彡
    0.75
    POSITIVE LOGITS
    et
    1.62
    '
    1.54
    i
    1.44
    ’
    1.38
    as
    1.35
    an
    1.16
    n
    1.16
    ي
    1.16
    on
    1.11
    a
    1.09
    Activations Density 0.000%

    No Known Activations