© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60817
    Prev
    Next
    INDEX
    Explanations

    build-up

    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_11_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
    ו
    0.80
    ت
    0.68
    o
    0.62
    い
    0.59
    ра
    0.57
    т
    0.56
    in
    0.53
    u
    0.52
    ا
    0.52
    t
    0.52
    POSITIVE LOGITS
    ),
    0.64
    =
    0.61
    )
    0.60
    iping
    0.57
    ≤
    0.56
    酸化
    0.55
     Lucifer
    0.54
    -
    0.54
     שני
    0.54
    ≥
    0.54
    Activations Density 0.003%

    No Known Activations