© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42416
    Prev
    Next
    INDEX
    Explanations

    next action or step

    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
    .
    0.78
     قریب
    0.77
     accanto
    0.73
    hesized
    0.72
    ем
    0.70
    een
    0.69
    ach
    0.68
    o
    0.68
    isection
    0.67
     adjacent
    0.66
    POSITIVE LOGITS
    That
    0.93
    THAT
    0.88
     that
    0.85
    that
    0.85
    Passengers
    0.84
    מ
    0.82
    ي
    0.79
    জ
    0.78
    א
    0.78
    ح
    0.78
    Activations Density 0.002%

    No Known Activations