© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42244
    Prev
    Next
    INDEX
    Explanations

    graduate and postgraduate education

    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_22_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
     alle
    0.43
     ಜನ
    0.43
    人々
    0.42
    δία
    0.41
     supplying
    0.41
    ouvrir
    0.40
    風
    0.40
     set
    0.40
    梘
    0.39
     installing
    0.39
    POSITIVE LOGITS
     
    0.42
     لتح
    0.41
     تعرف
    0.40
     Judging
    0.38
    
    0.37
    뇽
    0.37
     .$
    0.37
    쳤
    0.36
    itin
    0.36
    EMS
    0.36
    Activations Density 0.001%

    No Known Activations