© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 203171
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_25_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
     musul
    0.46
    нцикло
    0.44
    ውን
    0.44
     أيضًا
    0.43
    ﺖ
    0.43
     вклю
    0.43
     доклад
    0.43
    ḕ
    0.43
    ிற்கு
    0.43
    )'=='
    0.42
    POSITIVE LOGITS
     x
    0.49
     hip
    0.46
     is
    0.45
    fter
    0.44
    ately
    0.44
     hall
    0.44
     has
    0.44
    xas
    0.43
     canvas
    0.43
     can
    0.42
    Activations Density 0.000%

    No Known Activations