© 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. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 195643
    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_26_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
    broadcast
    0.46
     hyphen
    0.44
     doctrinal
    0.44
     अंतरराष्ट्रीय
    0.43
    {(\
    0.43
    {-\
    0.43
     税
    0.43
    {\
    0.42
     பொருளாதார
    0.42
    ：（
    0.42
    POSITIVE LOGITS
     وض
    0.52
    o
    0.49
    in
    0.48
    Charm
    0.40
     kurz
    0.39
    wert
    0.39
     charm
    0.38
     Umgebung
    0.38
    oost
    0.38
     bestimmt
    0.38
    Activations Density 0.000%

    No Known Activations