© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 213189
    Prev
    Next
    INDEX
    Explanations

    style/flair

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_43_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
    瞳
    0.39
     arrowhead
    0.37
    सिक
    0.36
    ებს
    0.36
    лик
    0.36
    lobulin
    0.36
    greedy
    0.36
    OTOS
    0.35
    
    0.35
    ভূতির
    0.34
    POSITIVE LOGITS
     swag
    0.80
     style
    0.78
     flair
    0.73
     estilo
    0.71
     Style
    0.70
     Sw
    0.66
     शैली
    0.66
    style
    0.64
    Style
    0.64
     swagger
    0.64
    Activations Density 0.003%

    No Known Activations