© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 217848
    Prev
    Next
    INDEX
    Explanations

    my previous

    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_31_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
    到一个
    0.38
     (--
    0.38
    игры
    0.38
    driver
    0.36
    镟
    0.36
     معه
    0.35
     യൂണി
    0.35
    在一个
    0.35
    delen
    0.35
     physiological
    0.34
    POSITIVE LOGITS
     tid
    0.40
    מ
    0.36
    otopic
    0.36
     fable
    0.34
    抖
    0.34
     Dem
    0.34
     pekerjaan
    0.33
    누
    0.33
     chore
    0.33
     PackageManager
    0.33
    Activations Density 0.003%

    No Known Activations