© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 93823
    Prev
    Next
    INDEX
    Explanations

    previous

    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_60_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     illustrious
    0.37
     велико
    0.35
    
    0.34
     Dö
    0.33
     ursprünglich
    0.33
     confluence
    0.33
    繳
    0.33
    ꉂ
    0.33
    щи
    0.33
    ་
    0.32
    POSITIVE LOGITS
     Prev
    2.53
    Prev
    2.52
    prev
    2.50
     prev
    2.48
     prevailing
    2.22
    전
    1.82
     prevail
    1.80
     전
    1.64
     prevailed
    1.59
     prevails
    1.56
    Activations Density 0.002%

    No Known Activations