© 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. 6578
    Prev
    Next
    INDEX
    Explanations

    `/` followed by `bin` or `local`

    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
     ressort
    0.37
     chats
    0.35
    abban
    0.34
    '];?>
    0.33
    𒋢
    0.33
     [`
    0.32
    FlatStyle
    0.32
     crest
    0.32
    (`./
    0.32
    真
    0.32
    POSITIVE LOGITS
     قواعد
    0.39
    cknowledg
    0.37
    endez
    0.37
    regulation
    0.35
    Regulation
    0.35
     acknowledge
    0.34
    irect
    0.34
     ಬೇ
    0.34
    頸
    0.33
    利
    0.33
    Activations Density 0.003%

    No Known Activations