© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 36990
    Prev
    Next
    INDEX
    Explanations

    dou, double

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Leverage
    0.42
    GC
    0.40
    asel
    0.40
    abet
    0.39
    aryn
    0.39
    ))(
    0.38
    ("")
    0.38
    SleepHours
    0.38
    Catherine
    0.37
    ʷ
    0.37
    POSITIVE LOGITS
     Dou
    0.61
     dou
    0.59
     DOU
    0.59
    Dou
    0.56
    dou
    0.52
     doubles
    0.51
     doubling
    0.48
     Doubles
    0.47
    శా
    0.45
     doubled
    0.42
    Activations Density 0.005%

    No Known Activations