© 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. 11517
    Prev
    Next
    INDEX
    Explanations

    visas, loans, otters, gas, air

    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
     entendido
    0.51
     wan
    0.49
    udi
    0.48
    Xbox
    0.47
    so
    0.47
    dul
    0.47
    ú
    0.46
     falta
    0.45
    ado
    0.45
    Casa
    0.45
    POSITIVE LOGITS
     класс
    0.52
    专题
    0.51
    Ꮈ
    0.51
     موضوع
    0.48
    elevator
    0.46
     Elevator
    0.46
     управ
    0.45
     izv
    0.45
     ;
    0.45
     непо
    0.44
    Activations Density 0.012%

    No Known Activations