© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 143611
    Prev
    Next
    INDEX
    Explanations

    reasons

    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_46_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
     about
    0.38
     kicking
    0.37
    chanics
    0.37
    sob
    0.37
     FN
    0.36
    ま
    0.36
    Furn
    0.36
     kich
    0.36
     furnish
    0.35
    inkan
    0.35
    POSITIVE LOGITS
     یونیورسٹی
    0.38
    疇
    0.37
     образу
    0.35
     التط
    0.35
     سلط
    0.35
     نقط
    0.34
     التى
    0.34
     reintroduced
    0.34
     punto
    0.34
    authent
    0.33
    Activations Density 0.012%

    No Known Activations