© 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
    2. Gemma-3-27B-IT
    3. 11-GEMMASCOPE-2-TRANSCODER-262K
    4. 91916
    Prev
    Next
    INDEX
    Explanations

    fmt.Println calls

    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
    ﺭ
    0.72
     Ll
    0.66
     
    0.64
    AR
    0.61
    URI
    0.61
    را
    0.61
    remos
    0.56
    ла
    0.56
    ream
    0.56
    UL
    0.56
    POSITIVE LOGITS
    ⴳ
    0.59
    ಾಯಿತು
    0.58
    ാവ
    0.57
    ξη
    0.57
     cigars
    0.56
    electrical
    0.56
    kelly
    0.55
     sommeil
    0.54
     armies
    0.54
    endswith
    0.54
    Activations Density 0.001%

    No Known Activations