© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 206112
    Prev
    Next
    INDEX
    Explanations

    turbine blades

    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_19_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
    assured
    0.52
    ت
    0.48
    "..
    0.47
    ))%>%
    0.47
    zt
    0.46
    ي
    0.44
    ൂടെ
    0.44
    ുമായി
    0.44
    й
    0.44
     سمیت
    0.43
    POSITIVE LOGITS
     bandas
    0.52
     efectivos
    0.48
     gói
    0.45
     물
    0.44
     koordin
    0.43
     aval
    0.43
     colect
    0.42
     poly
    0.42
     fogo
    0.42
     agua
    0.42
    Activations Density 0.000%

    No Known Activations