© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 219553
    Prev
    Next
    INDEX
    Explanations

    tracks and traces

    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_47_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
     trace
    2.78
     traces
    2.73
    Trace
    2.44
    trace
    2.42
     Trace
    2.41
    traces
    2.31
     traced
    1.92
    痕
    1.91
     tracing
    1.89
    TRACE
    1.86
    POSITIVE LOGITS
    كشن
    0.40
     झड़
    0.38
     uptime
    0.38
     pulling
    0.37
    )^{
    0.35
    ेक्षित
    0.34
    เขต
    0.34
    feer
    0.34
    Reporting
    0.34
    ობით
    0.34
    Activations Density 0.003%

    No Known Activations