© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53138
    Prev
    Next
    INDEX
    Explanations

    business intelligence data and dashboards

    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_31_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
    บาย
    0.38
    Documentation
    0.37
     ਜਾਣ
    0.37
    氫
    0.37
    ंबे
    0.36
    برد
    0.35
    Hydrogen
    0.35
     HST
    0.35
     বহুদিন
    0.35
    鎳
    0.35
    POSITIVE LOGITS
     fascinating
    0.40
     intriguing
    0.39
     dashboards
    0.38
     противо
    0.37
     Muss
    0.37
    så
    0.37
     hekt
    0.36
     meningitis
    0.36
    imid
    0.36
    ޫ
    0.36
    Activations Density 0.080%

    No Known Activations