© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44555
    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_22_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
    চ্চ
    0.45
    À
    0.45
    Arsenal
    0.42
    Europe
    0.41
    file
    0.40
    Nature
    0.39
    Figures
    0.39
    Evolution
    0.39
    法則
    0.39
     fora
    0.39
    POSITIVE LOGITS
     밝혔
    0.46
    皘
    0.43
     तुक
    0.43
     ಇ
    0.43
    \_
    0.42
    ニック
    0.41
     latérales
    0.41
    掍
    0.41
     waxing
    0.40
    둰
    0.40
    Activations Density 0.000%

    No Known Activations