© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 78258
    Prev
    Next
    INDEX
    Explanations

    country joined European organizations

    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
    Elig
    0.44
    Wire
    0.39
    USA
    0.39
    ✈
    0.38
     वर्त
    0.38
     eligible
    0.38
    uml
    0.38
     Eligible
    0.37
     চট্টগ্রামে
    0.37
    eligible
    0.37
    POSITIVE LOGITS
     lord
    0.44
    lord
    0.38
     laughing
    0.35
     nhánh
    0.35
     cleaning
    0.35
     fou
    0.35
    昦
    0.34
     brinqu
    0.34
     Lord
    0.34
    ас
    0.34
    Activations Density 0.005%

    No Known Activations