© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 12107
    Prev
    Next
    INDEX
    Explanations

    video and Khan Academy

    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_13_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
     menj
    0.55
    O
    0.54
    ilver
    0.51
     является
    0.50
     ሁለት
    0.50
     Novartis
    0.50
     مولانا
    0.49
     老
    0.48
    ᱷ
    0.48
     mening
    0.47
    POSITIVE LOGITS
     فيديو
    0.72
     vidéos
    0.69
     videolar
    0.68
     वीडियो
    0.66
     videos
    0.66
     vidéo
    0.65
     vídeos
    0.64
    Video
    0.63
     vídeo
    0.63
     ভিডিও
    0.61
    Activations Density 0.062%

    No Known Activations