© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 30745
    Prev
    Next
    INDEX
    Explanations

    a

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    usahaan
    0.44
    ﺓ
    0.43
    ریع
    0.42
    IdentityProvider
    0.40
    আনুশকা
    0.39
     இவரது
    0.39
    ᖅ
    0.38
     تھا۔
    0.37
    ضة
    0.37
     sırasında
    0.37
    POSITIVE LOGITS
    andan
    0.41
     hot
    0.39
     Guin
    0.39
    扡
    0.38
     UGC
    0.38
    powers
    0.38
    Hot
    0.37
    ocken
    0.36
    hot
    0.36
    ogni
    0.36
    Activations Density 0.005%

    No Known Activations