© 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. 30142
    Prev
    Next
    INDEX
    Explanations

    gold foil stamping accents

    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
    сер
    0.40
    built
    0.39
    cup
    0.37
     epidermal
    0.37
    病
    0.37
    CDCl
    0.36
     audi
    0.36
    fal
    0.35
     equivari
    0.35
    Exam
    0.35
    POSITIVE LOGITS
     foil
    0.90
     Foil
    0.83
     foils
    0.76
     foiled
    0.71
    foil
    0.71
     stamped
    0.64
    Stamped
    0.64
     stamping
    0.62
    箔
    0.56
    foils
    0.55
    Activations Density 0.042%

    No Known Activations