© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12754
    Prev
    Next
    INDEX
    Explanations

    organ transplant, rejection, failure, growth

    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
     الاول
    0.28
     草
    0.25
    开始
    0.25
     barracks
    0.24
    ологии
    0.24
     başlat
    0.24
    ４
    0.23
     Каждый
    0.23
    ለኛ
    0.23
    鹳
    0.23
    POSITIVE LOGITS
    ada
    0.29
    dice
    0.28
    izada
    0.27
    resa
    0.27
     Lung
    0.27
     brainstorming
    0.26
    ige
    0.26
    lung
    0.26
    ن
    0.25
    "
    0.25
    Activations Density 0.004%

    No Known Activations