© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7620
    Prev
    Next
    INDEX
    Explanations

    terminal or

    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_39_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
     общества
    0.38
     núcleo
    0.37
     circulación
    0.37
     بیٹھ
    0.36
    ponden
    0.35
     网
    0.34
    Netflix
    0.33
     circulation
    0.33
    ripción
    0.33
     Binding
    0.33
    POSITIVE LOGITS
     высоких
    0.42
    stylish
    0.41
     kaz
    0.39
     arom
    0.38
    辣
    0.38
    ത്തക
    0.38
     ಆಧ
    0.38
    ក្ខ
    0.38
    كنولوج
    0.37
     reopening
    0.37
    Activations Density 0.018%

    No Known Activations