© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80008
    Prev
    Next
    INDEX
    Explanations

    Russian and Thai conjunctions

    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_0_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
    ing
    2.27
    g
    2.13
    p
    2.03
    k
    2.02
    т
    1.78
    й
    1.66
    ع
    1.63
    า
    1.63
    us
    1.60
    y
    1.60
    POSITIVE LOGITS
    ため
    1.46
    사
    1.27
     มัน
    1.23
    ের
    1.17
    ма
    1.07
     it
    1.05
    ມັນ
    1.05
    บ
    1.05
     luas
    1.03
     erster
    1.02
    Activations Density 0.001%

    No Known Activations