© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 164731
    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
    (':')[
    0.36
    $}}
    0.36
     अतुल
    0.35
    closed
    0.35
     caveat
    0.34
     pocket
    0.34
     Pocket
    0.34
     apologies
    0.34
    atured
    0.34
    Pocket
    0.34
    POSITIVE LOGITS
     presentó
    0.43
     ANTON
    0.41
    䡋
    0.39
     गावा
    0.39
     항
    0.38
    ="../../
    0.38
     Village
    0.38
     صبر
    0.37
    Village
    0.36
     Vec
    0.36
    Activations Density 0.000%

    No Known Activations