© 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. 201259
    Prev
    Next
    INDEX
    Explanations

    Champs-Élysées

    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
     サン
    0.41
    lare
    0.40
    サン
    0.40
     Babe
    0.39
     beats
    0.39
    }[!
    0.38
    wdir
    0.38
     Baxter
    0.37
    巴
    0.37
     Beat
    0.36
    POSITIVE LOGITS
    വസ
    0.42
    互联网
    0.38
    diam
    0.38
    ཆ
    0.37
    构
    0.36
     endroit
    0.36
    chende
    0.36
    iteness
    0.35
    आईटी
    0.35
     camphor
    0.35
    Activations Density 0.000%

    No Known Activations