© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4163
    Prev
    Next
    INDEX
    Explanations

    owner or manager

    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_39_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
     బా
    0.45
    USB
    0.40
     chercheurs
    0.39
     toppers
    0.39
     tungsten
    0.38
     cyber
    0.38
     payers
    0.38
     =-\
    0.37
    algar
    0.37
    峹
    0.37
    POSITIVE LOGITS
     propietario
    0.56
     Manager
    0.55
     propiet
    0.54
     proprietor
    0.53
     propriétaire
    0.52
    Owner
    0.51
     propriet
    0.50
     owner
    0.50
     Owner
    0.49
     manager
    0.49
    Activations Density 0.034%

    No Known Activations