© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    4. 139412
    Prev
    Next
    INDEX
    Explanations

    introducing

    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_12_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
    РО
    0.68
    導入
    0.68
    р
    0.68
    грам
    0.66
    вающих
    0.66
    Ф
    0.66
    ктак
    0.65
    탄소년
    0.64
    Қ
    0.64
    ковского
    0.64
    POSITIVE LOGITS
    ]
    0.73
     údaje
    0.67
     [
    0.66
    	
    0.64
     seminar
    0.61
     (
    0.61
     in
    0.60
     In
    0.60
     college
    0.60
     minister
    0.60
    Activations Density 0.001%

    No Known Activations