© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 200558
    Prev
    Next
    INDEX
    Explanations

    Mongol, Song Dynasty, China

    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_37_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
    Fatal
    0.40
     Loyola
    0.38
    ૫
    0.38
    spacerItem
    0.36
     Inference
    0.36
    啉
    0.35
     DEF
    0.35
    лями
    0.35
     Med
    0.35
     Rar
    0.35
    POSITIVE LOGITS
     Kub
    0.45
     pulse
    0.45
     Mongols
    0.45
    蒙古
    0.44
    宋
    0.43
     Mongol
    0.43
     Templ
    0.42
     mong
    0.42
     pulsar
    0.42
    脉
    0.42
    Activations Density 0.002%

    No Known Activations