© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9983
    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_40_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
    吞
    0.43
     একথা
    0.39
     옳은
    0.39
    asek
    0.38
     মুজিবর
    0.38
    ленные
    0.37
    fluoro
    0.37
     कृत
    0.37
     favourite
    0.36
    糠
    0.36
    POSITIVE LOGITS
     society
    0.52
    씨
    0.49
     Society
    0.43
    verlag
    0.43
    society
    0.43
     societies
    0.42
     SOCIETY
    0.42
     المجتمع
    0.40
     社
    0.40
     patriarchal
    0.40
    Activations Density 0.019%

    No Known Activations