© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199550
    Prev
    Next
    INDEX
    Explanations

    Next and Finish buttons

    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
     ل
    0.63
     о
    0.60
     l
    0.58
    ме
    0.58
     кли
    0.58
    م
    0.57
    й
    0.56
    сы
    0.54
    ны
    0.54
     من
    0.54
    POSITIVE LOGITS
          
    0.61
     Infect
    0.56
     Pestic
    0.55
    December
    0.54
     Because
    0.53
    Tracks
    0.52
     Trento
    0.52
         
    0.51
     Infants
    0.51
     necessario
    0.50
    Activations Density 0.001%

    No Known Activations