© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103215
    Prev
    Next
    INDEX
    Explanations

    zero followed by concept

    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_1_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
     và
    1.13
     Hồng
    1.13
     Гу
    1.06
     Бүгенге
    1.05
     Верх
    1.04
     và
    1.03
     Վ
    1.02
     esas
    0.99
     njega
    0.98
     politiche
    0.98
    POSITIVE LOGITS
    t
    1.72
    ع
    1.38
    ด
    1.37
    ur
    1.35
    ن
    1.35
    ت
    1.34
    o
    1.30
    s
    1.30
    f
    1.27
    R
    1.27
    Activations Density 0.001%

    No Known Activations