© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 33554
    Prev
    Next
    INDEX
    Explanations

    public static class

    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_40_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
     private
    0.49
    Private
    0.47
    PRIVATE
    0.46
    private
    0.45
    私
    0.44
     Private
    0.43
     PRIVATE
    0.43
     निजी
    0.40
     私
    0.39
     privés
    0.39
    POSITIVE LOGITS
    ijev
    0.27
     humidity
    0.26
    нику
    0.26
     ün
    0.26
    흄
    0.25
    邝
    0.25
    intention
    0.25
    ।--
    0.25
    াচার
    0.25
    繋がりたい
    0.24
    Activations Density 0.000%

    No Known Activations