© 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. 9842
    Prev
    Next
    INDEX
    Explanations

    craft, hip, cocktail, artisan, modern, 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
     Representations
    0.37
    淋
    0.37
     McGraw
    0.37
    ச்சத்து
    0.36
     inext
    0.34
    맑
    0.33
     representations
    0.33
    ूँ
    0.33
    쮿
    0.33
     personnels
    0.32
    POSITIVE LOGITS
     artisan
    0.96
     hipster
    0.87
     artisanal
    0.84
     Artisan
    0.80
    hipster
    0.77
     craft
    0.74
     artisans
    0.71
     brewery
    0.71
     Artis
    0.70
     beer
    0.67
    Activations Density 0.103%

    No Known Activations