© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 33329
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     qu
    0.35
    燡
    0.34
    суа
    0.34
    estad
    0.34
     Azure
    0.33
    يدات
    0.33
     Estrada
    0.33
     Супер
    0.33
     والا
    0.32
     Θ
    0.32
    POSITIVE LOGITS
     initiated
    0.98
     initiate
    0.90
     trigger
    0.88
     Initi
    0.88
     inici
    0.86
     triggered
    0.86
    启动
    0.86
     Initiate
    0.84
     initiates
    0.83
     iniciado
    0.82
    Activations Density 0.172%

    No Known Activations