© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    4. 136747
    Prev
    Next
    INDEX
    Explanations

    ver- prefixes

    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
     elke
    0.43
     Pä
    0.39
    վ
    0.39
     ছিলেন
    0.38
     verg
    0.38
     Beyoncé
    0.38
     equip
    0.38
     philos
    0.38
    抺
    0.37
     ενεργ
    0.37
    POSITIVE LOGITS
     несмотря
    0.41
     Knox
    0.37
    پيديا
    0.37
    先后
    0.36
     bár
    0.36
     добиться
    0.36
     رغم
    0.36
    
    0.36
     BitmapFactory
    0.35
    ):=\
    0.35
    Activations Density 0.001%

    No Known Activations