© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110860
    Prev
    Next
    INDEX
    Explanations

    flare up, flare out, flare stack, Flare Blitz

    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_2_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
    ت
    2.34
    on
    1.77
    т
    1.70
    ות
    1.64
    ר
    1.64
    고
    1.62
    us
    1.59
    ত
    1.57
    ع
    1.52
    る
    1.50
    POSITIVE LOGITS
     ότι
    1.05
     únic
    1.00
     определён
    0.98
     bescherm
    0.96
     ин
    0.95
    ،
    0.94
     обнов
    0.93
     enggak
    0.91
     опреде
    0.90
     informativa
    0.90
    Activations Density 0.001%

    No Known Activations