© 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. 225235
    Prev
    Next
    INDEX
    Explanations

    code snippets and queries

    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
    А
    0.73
     тях
    0.70
     l
    0.70
     இங்கு
    0.69
    </strong>
    0.68
    Ν
    0.67
     свето
    0.66
    Е
    0.66
     п
    0.65
     Bally
    0.65
    POSITIVE LOGITS
    zijde
    0.66
     Jullie
    0.64
    ()")
    0.64
    OrCreate
    0.63
    capped
    0.62
    coord
    0.62
    konto
    0.61
    lepší
    0.60
    actica
    0.60
    tareas
    0.59
    Activations Density 0.000%

    No Known Activations