© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 158294
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
     rattling
    0.50
     Ratt
    0.46
    atomic
    0.44
     unrivalled
    0.44
    ittarius
    0.43
     rattles
    0.42
     nigh
    0.39
    儕
    0.39
     atomic
    0.39
     billet
    0.39
    POSITIVE LOGITS
    ор
    0.42
    ನ್ನೂ
    0.41
    젤
    0.40
    돋
    0.39
    郊
    0.38
    崔
    0.38
    rags
    0.38
    БК
    0.38
    Vý
    0.37
    Mé
    0.36
    Activations Density 0.000%

    No Known Activations