© 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. 29953
    Prev
    Next
    INDEX
    Explanations

    every hour

    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
     attends
    0.45
     attend
    0.44
     attending
    0.43
     Attend
    0.43
     पीछा
    0.41
    attendance
    0.40
    Attend
    0.39
    ":[{"
    0.38
    ério
    0.38
    ffes
    0.38
    POSITIVE LOGITS
    小时
    0.42
     وكل
    0.38
    欷
    0.37
     Simulations
    0.37
     Hourly
    0.37
    Module
    0.36
    小時
    0.36
     Raw
    0.36
    Simulation
    0.36
     COL
    0.36
    Activations Density 0.001%

    No Known Activations