© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4794
    Prev
    Next
    INDEX
    Explanations

    packet drops, memory address, metal powders

    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_40_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
    ներ
    0.41
     vre
    0.39
    ларда
    0.37
    Ruth
    0.36
    𝑳
    0.35
    ダイ
    0.35
    माही
    0.35
     Hare
    0.34
     vacuum
    0.34
    庚
    0.34
    POSITIVE LOGITS
    MUX
    0.37
    jobs
    0.36
    ตร์
    0.36
     Brooks
    0.35
    udder
    0.35
     ജീവിത
    0.35
    ύ
    0.34
    working
    0.34
     stoves
    0.34
     juridique
    0.34
    Activations Density 0.178%

    No Known Activations