© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 205776
    Prev
    Next
    INDEX
    Explanations

    Eratosthenes

    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_20_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
    infested
    0.50
    Mana
    0.44
    ть
    0.42
    Furniture
    0.42
    のこ
    0.41
    tores
    0.41
    ẩ
    0.39
    kej
    0.39
    
    0.39
    Mrs
    0.38
    POSITIVE LOGITS
     script
    0.47
     détecter
    0.45
     patrocin
    0.45
    澧
    0.45
     búsqueda
    0.44
    표
    0.42
     April
    0.42
     दिखता
    0.42
     محاسبه
    0.42
     mesma
    0.42
    Activations Density 0.000%

    No Known Activations