© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 102354
    Prev
    Next
    INDEX
    Explanations

    skip connections

    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_44_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
     Windsor
    0.41
    桥
    0.38
    橋
    0.37
     Marc
    0.37
     Bartlett
    0.37
     OTHERWISE
    0.35
     hydroxy
    0.35
     HS
    0.35
    prevState
    0.34
     Marqu
    0.34
    POSITIVE LOGITS
     സേ
    0.41
     matter
    0.38
     Income
    0.37
    aisesti
    0.36
    ческий
    0.35
     contient
    0.35
    лыгы
    0.35
     т
    0.35
     logements
    0.35
    шай
    0.35
    Activations Density 0.039%

    No Known Activations