© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 170112
    Prev
    Next
    INDEX
    Explanations

    medical procedures

    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_56_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
    Approach
    0.42
     لنا
    0.39
    特集
    0.36
    扼
    0.36
    feature
    0.35
    🚞
    0.35
     रण
    0.34
    hane
    0.34
    Appro
    0.34
     RtlOverlay
    0.34
    POSITIVE LOGITS
     Procedure
    0.45
     procedure
    0.40
     Scotland
    0.39
    Procedure
    0.38
     Reflex
    0.38
    ႈ
    0.38
    
    0.38
     practise
    0.37
     Nutrient
    0.37
     Asalamualaikum
    0.37
    Activations Density 0.001%

    No Known Activations