© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78151
    Prev
    Next
    INDEX
    Explanations

    shops and related places

    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
    Negative Logits
    ri
    1.57
    la
    1.44
    l
    1.41
    m
    1.39
    בר
    1.30
    lí
    1.27
    g
    1.26
    k
    1.26
     a
    1.23
    ká
    1.17
    POSITIVE LOGITS
    س
    1.56
    2
    1.55
    는
    1.54
    ت
    1.27
    ה
    1.27
    이라고
    1.24
    是
    1.23
    เป็น
    1.20
    이랑
    1.20
    on
    1.20
    Activations Density 0.000%

    No Known Activations