© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59631
    Prev
    Next
    INDEX
    Explanations

    `goroutines` and `json`

    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_11_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
     உலோக
    0.41
    ͑
    0.40
    ка
    0.40
    sty
    0.39
    ተር
    0.39
     रोड
    0.39
    мое
    0.39
    code
    0.39
    ch
    0.38
     estilos
    0.38
    POSITIVE LOGITS
     lunga
    0.41
     be
    0.40
     £
    0.38
     tariff
    0.38
     long
    0.38
     [];
    0.38
    同时也
    0.37
     nee
    0.37
    錤
    0.37
     reum
    0.37
    Activations Density 0.072%

    No Known Activations