© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 45055
    Prev
    Next
    INDEX
    Explanations

    Java stream filter

    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_10_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
    |".
    0.53
     Haag
    0.51
    StaticHandler
    0.51
     eyebrows
    0.50
    CubeSize
    0.50
    StructOf
    0.49
    娆
    0.49
    Да
    0.49
     СПб
    0.48
    广
    0.48
    POSITIVE LOGITS
    ת
    0.55
     to
    0.53
     zato
    0.46
     bệnh
    0.46
    adece
    0.44
     ziek
    0.44
     tuto
    0.43
     če
    0.43
     shrink
    0.43
     monoch
    0.43
    Activations Density 0.000%

    No Known Activations