© 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. 157
    Prev
    Next
    INDEX
    Explanations

    year/path/numbers

    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
     Broward
    0.40
    蚤
    0.39
     Fournier
    0.39
     Munster
    0.39
    閎
    0.38
    爾
    0.38
     საერთ
    0.37
    льным
    0.36
     Swezey
    0.36
    ন্ন
    0.35
    POSITIVE LOGITS
    Picking
    0.38
     transduction
    0.37
    屾
    0.37
     निजामा
    0.37
    picking
    0.33
    坨
    0.33
     dòng
    0.33
    documentElement
    0.32
     picking
    0.32
    ()+
    0.32
    Activations Density 0.016%

    No Known Activations