© 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. 24800
    Prev
    Next
    INDEX
    Explanations

    flex layout properties

    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
    ка
    0.91
    (
    0.82
    ли
    0.74
    గ
    0.74
    /
    0.73
    a
    0.70
    ্ব
    0.67
    জ
    0.67
    ری
    0.66
    აკ
    0.66
    POSITIVE LOGITS
     tepung
    0.66
    ésére
    0.64
    ención
    0.63
     rabies
    0.62
    atal
    0.62
     type
    0.61
    otherapy
    0.61
     denna
    0.59
    elerinin
    0.59
     flour
    0.59
    Activations Density 0.004%

    No Known Activations