© 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. 15899
    Prev
    Next
    INDEX
    Explanations

    party or celebration events

    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
    食
    0.73
     food
    0.66
     meals
    0.65
    Meals
    0.65
    food
    0.63
     Meals
    0.63
    食べ
    0.60
     খাবার
    0.60
     eats
    0.59
    밥
    0.59
    POSITIVE LOGITS
     geb
    0.38
    在家
    0.38
    hat
    0.37
     ind
    0.36
    arendon
    0.36
     quiet
    0.36
     grill
    0.35
     germ
    0.34
    షా
    0.34
     البروت
    0.34
    Activations Density 0.056%

    No Known Activations