© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35849
    Prev
    Next
    INDEX
    Explanations

    world

    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_11_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
    時
    0.71
    ઝ
    0.70
     نہيں
    0.68
     ರಿಂದ
    0.64
    ínt
    0.64
     deň
    0.63
    ٻ
    0.63
     ۾
    0.63
     நிலையத்தில்
    0.62
    филлер
    0.62
    POSITIVE LOGITS
     world
    0.73
     World
    0.63
    ls
    0.63
     international
    0.60
    :
    0.60
     globe
    0.59
     WORLD
    0.59
    World
    0.58
     alienation
    0.57
    0
    0.57
    Activations Density 0.034%

    No Known Activations