© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 25227
    Prev
    Next
    INDEX
    Explanations

    benchmarking and evaluation

    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_10_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
    in
    1.16
    u
    0.85
    en
    0.66
    maxim
    0.65
    q
    0.65
    ma
    0.65
    em
    0.64
    t
    0.64
    inase
    0.63
    as
    0.63
    POSITIVE LOGITS
     aguas
    0.66
     benchmarks
    0.65
    ول
    0.59
    ਮ
    0.57
    ض
    0.56
     कामगिरी
    0.55
    ți
    0.55
    υ
    0.55
    larımız
    0.54
    <0xA5>
    0.54
    Activations Density 0.021%

    No Known Activations