© 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. 230468
    Prev
    Next
    INDEX
    Explanations

    select the best answer

    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
    at
    1.38
    ა
    1.11
    ا
    0.98
    ী
    0.97
    on
    0.93
    א
    0.93
    Gö
    0.89
    ל
    0.87
    ق
    0.86
    ul
    0.84
    POSITIVE LOGITS
     in
    1.19
    ่
    1.05
     the
    0.93
     pinpoint
    0.91
     as
    0.88
    )[
    0.85
     σε
    0.84
    kten
    0.83
     supplemented
    0.82
    s
    0.82
    Activations Density 0.002%

    No Known Activations