© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 215744
    Prev
    Next
    INDEX
    Explanations

    skimming

    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_5_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
    د
    1.08
    م
    1.07
     be
    1.03
    ق
    0.99
        
    0.96
    ↵
    0.94
    də
    0.93
     Nā
    0.90
    ни
    0.89
    ر
    0.88
    POSITIVE LOGITS
    ant
    0.92
    he
    0.88
    9
    0.87
    2
    0.85
    inin
    0.84
    ra
    0.84
    ینگ
    0.82
    ong
    0.81
    ่ง
    0.81
    ட்ட
    0.80
    Activations Density 0.000%

    No Known Activations