© 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. 2478
    Prev
    Next
    INDEX
    Explanations

    French film and crime thrillers

    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
     palaces
    0.40
     withheld
    0.39
    holo
    0.39
     MIT
    0.38
    コンサート
    0.38
     STORM
    0.38
     బీజేపీ
    0.38
     ಬಿಜೆಪಿ
    0.37
    楤
    0.37
     serif
    0.37
    POSITIVE LOGITS
    uteur
    0.46
    Before
    0.43
     Before
    0.42
    Sin
    0.41
     قبل
    0.39
    ource
    0.38
     Busy
    0.38
    busy
    0.38
    Antes
    0.38
    Breakfast
    0.37
    Activations Density 0.066%

    No Known Activations