© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 36624
    Prev
    Next
    INDEX
    Explanations

    PDF reader/writer libraries

    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
    ’
    0.80
    ς
    0.64
    做
    0.63
     PDF
    0.62
    ‘
    0.61
    이나
    0.60
    すと
    0.59
    必须要
    0.59
    мя
    0.58
     klass
    0.57
    POSITIVE LOGITS
     and
    0.91
     as
    0.82
     are
    0.81
    v
    0.75
    0
    0.71
    ال
    0.67
    <0x80>
    0.64
    ری
    0.63
    nies
    0.62
    istici
    0.62
    Activations Density 0.003%

    No Known Activations