© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 49670
    Prev
    Next
    INDEX
    Explanations

    Korean particles (postpositions)

    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_31_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
    滞
    0.20
    bounded
    0.18
    滯
    0.18
     desconto
    0.18
    discount
    0.17
    extreme
    0.17
    extré
    0.17
    ROI
    0.17
     extrémités
    0.17
     pestaña
    0.17
    POSITIVE LOGITS
     светло
    0.18
     jer
    0.18
    涉及
    0.18
     }-\
    0.17
     cioè
    0.17
     conhecer
    0.17
    щ
    0.17
    コの
    0.17
     tenu
    0.17
    obacterium
    0.17
    Activations Density 0.001%

    No Known Activations