© 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. 46723
    Prev
    Next
    INDEX
    Explanations

    H-1B visa

    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
    .
    0.77
    Ν
    0.74
    ^
    0.71
    ной
    0.70
    ная
    0.69
    ди
    0.68
    Б
    0.67
    ных
    0.66
    ู
    0.66
     conci
    0.64
    POSITIVE LOGITS
    on
    0.93
    am
    0.77
    hazardous
    0.73
    amant
    0.71
    ار
    0.70
    ztal
    0.68
    geht
    0.67
    ंटिक
    0.65
    ak
    0.64
    have
    0.64
    Activations Density 0.001%

    No Known Activations