© 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. 78371
    Prev
    Next
    INDEX
    Explanations

    geospatial applications and analysis

    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
    y
    1.61
    1
    1.55
    ic
    1.51
    কে
    1.43
    ة
    1.40
    ست
    1.39
    w
    1.37
    ט
    1.34
    in
    1.34
    v
    1.33
    POSITIVE LOGITS
    ل
    1.46
    ка
    1.38
    ۰
    1.31
     are
    1.24
     ナ
    1.18
    nya
    1.17
    jší
    1.15
     as
    1.13
    র
    1.13
    지는
    1.12
    Activations Density 0.000%

    No Known Activations