© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 67557
    Prev
    Next
    INDEX
    Explanations

    strings . sequences

    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_41_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
    ɾ
    0.44
    splitting
    0.43
    Cec
    0.41
    Attk
    0.41
    Bott
    0.40
    锰
    0.39
    PostConstruct
    0.39
     klare
    0.38
    Ced
    0.38
    Spl
    0.38
    POSITIVE LOGITS
     المقدم
    0.39
     workers
    0.39
     xr
    0.37
     श्रमिकों
    0.34
     العامل
    0.34
    列
    0.34
     자주
    0.34
     없어
    0.33
     sequences
    0.33
     ز
    0.33
    Activations Density 0.000%

    No Known Activations