© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199423
    Prev
    Next
    INDEX
    Explanations

    bursts of acceleration

    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_12_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
     आर्मी
    0.64
    arrivalTime
    0.64
    garian
    0.62
    д
    0.61
    havam
    0.61
    ⇰
    0.61
    теры
    0.60
    vents
    0.59
    tiden
    0.59
    मणि
    0.59
    POSITIVE LOGITS
    /
    0.62
    on
    0.58
     E
    0.54
     i
    0.54
     و
    0.51
     AND
    0.51
     &&
    0.50
    $
    0.49
     spr
    0.48
     CL
    0.48
    Activations Density 0.000%

    No Known Activations