© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 213921
    Prev
    Next
    INDEX
    Explanations

    peak

    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_47_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
    мышлен
    0.43
     espada
    0.39
    
    0.37
     戦
    0.35
    อรี่
    0.35
    лете
    0.35
    agati
    0.35
    мма
    0.35
     ру
    0.34
    
    0.34
    POSITIVE LOGITS
    मिति
    0.39
     kad
    0.39
     Szym
    0.39
     Dhawan
    0.39
     Kad
    0.38
    扦
    0.38
    avk
    0.38
     Hud
    0.38
     twists
    0.38
     Omer
    0.37
    Activations Density 0.002%

    No Known Activations