© 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. 36045
    Prev
    Next
    INDEX
    Explanations

    HL7 Fields

    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
     سيد
    0.75
     bibliothèque
    0.75
     truncate
    0.73
    ról
    0.72
    ről
    0.72
    َى
    0.72
    ী
    0.71
    <0x80>
    0.70
    .
    0.70
    ють
    0.66
    POSITIVE LOGITS
    л
    0.79
    st
    0.71
    '।
    0.71
    compliant
    0.70
    po
    0.70
    factors
    0.70
    '
    0.68
    $),
    0.66
    genome
    0.66
    styr
    0.66
    Activations Density 0.001%

    No Known Activations