© 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. 3011
    Prev
    Next
    INDEX
    Explanations

    surgical instruments or medical procedures

    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
    📌
    0.36
    審
    0.35
     initi
    0.34
     স্ল
    0.34
    яна
    0.34
    멋
    0.32
     தர
    0.32
    禹
    0.32
    ุด
    0.31
    mtq
    0.31
    POSITIVE LOGITS
     saline
    0.52
     Sal
    0.42
    δό
    0.41
     salty
    0.40
    Bab
    0.38
    Sally
    0.37
    dim
    0.35
    Sal
    0.34
     saltwater
    0.34
    C
    0.34
    Activations Density 0.030%

    No Known Activations