© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 30539
    Prev
    Next
    INDEX
    Explanations

    F. Scott Fitzgerald, The Great Gatsby

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
     साक्षी
    0.40
    Suk
    0.37
    xadmin
    0.37
    سكري
    0.36
    蚁
    0.36
     Wilkes
    0.36
    Admin
    0.35
    സു
    0.35
     anticoagulant
    0.35
     Sul
    0.35
    POSITIVE LOGITS
     Monter
    0.42
     Fasc
    0.40
    孕
    0.37
    ثنين
    0.37
     Gatsby
    0.37
    intage
    0.36
    রাল
    0.36
     सेक्टर
    0.35
    IERC
    0.35
    Zj
    0.35
    Activations Density 0.014%

    No Known Activations