© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23494
    Prev
    Next
    INDEX
    Explanations

    invent/create

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     выбра
    0.40
     scelto
    0.39
     বেঁ
    0.39
     منتخب
    0.38
     henne
    0.38
    尽量
    0.37
     selten
    0.37
    選
    0.37
     seldom
    0.37
     ആരാ
    0.37
    POSITIVE LOGITS
     founded
    0.73
     invented
    0.70
     designed
    0.67
     convince
    0.66
     designing
    0.63
     convinces
    0.63
     invent
    0.62
     propose
    0.62
     devised
    0.61
     Designed
    0.61
    Activations Density 0.041%

    No Known Activations