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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 204101
    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_46_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
     مست
    0.39
     medo
    0.38
    ications
    0.38
    Mesh
    0.37
     недостаточно
    0.37
     caes
    0.37
    Michel
    0.37
    谢
    0.37
    संग
    0.36
    ื่ม
    0.36
    POSITIVE LOGITS
    ভির
    0.40
    рос
    0.38
     fixes
    0.38
     ဗ
    0.38
     Bapt
    0.37
    rstrip
    0.37
     Estat
    0.36
    uerre
    0.35
     fixe
    0.35
    willReturn
    0.34
    Activations Density 0.000%

    No Known Activations