© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 79464
    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_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
    uées
    0.40
     ఇప్పటికే
    0.39
     negociación
    0.38
     customary
    0.37
    囍
    0.37
     acepta
    0.36
     zeuden
    0.36
     déjà
    0.36
     দাঁড়িয়ে
    0.36
    赡
    0.35
    POSITIVE LOGITS
    蛲
    0.42
    maketitle
    0.40
    稼
    0.40
    Ep
    0.39
     Hoover
    0.39
    प्रा
    0.38
    ST
    0.38
     glau
    0.38
    Má
    0.36
     φυσ
    0.36
    Activations Density 0.000%

    No Known Activations