© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 30119
    Prev
    Next
    INDEX
    Explanations

    Google search

    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_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
     Reward
    0.39
     Devils
    0.38
    Queue
    0.36
     }\
    0.36
     devils
    0.36
    }\
    0.36
     ThemeData
    0.36
    selectTable
    0.36
     Reload
    0.35
     دانشج
    0.35
    POSITIVE LOGITS
    鄱
    0.40
     prol
    0.37
    look
    0.35
    wear
    0.35
    вши
    0.34
     linkages
    0.33
     vagas
    0.33
     slots
    0.33
     குறிப்பிட
    0.32
    諫
    0.32
    Activations Density 0.002%

    No Known Activations