© 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. 106694
    Prev
    Next
    INDEX
    Explanations

    Semmelweis university, Vulkan vs GPU

    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
    '
    1.61
    -
    1.27
    вих
    0.99
    icates
    0.96
    ions
    0.93
    <
    0.91
    ush
    0.89
    ifications
    0.89
    rik
    0.88
    marks
    0.88
    POSITIVE LOGITS
    다
    1.39
     on
    1.36
    ق
    1.31
    ת
    1.31
    ח
    1.28
    ين
    1.21
    ה
    1.21
     。
    1.20
    ના
    1.20
    م
    1.19
    Activations Density 0.000%

    No Known Activations