© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 126373
    Prev
    Next
    INDEX
    Explanations

    você / le + verb

    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_3_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
    ه
    0.88
    ك
    0.82
    ول
    0.80
    вает
    0.74
    a
    0.73
     угла
    0.72
     encuentren
    0.70
    )];
    0.69
     нарушения
    0.69
    ри
    0.68
    POSITIVE LOGITS
    ↵
    0.94
    ม
    0.86
    나
    0.86
    '
    0.83
    </h2>
    0.82
     two
    0.69
     polyurethane
    0.69
     graduate
    0.69
     one
    0.68
     lengthy
    0.68
    Activations Density 0.001%

    No Known Activations