© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 124514
    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_37_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
    Marcus
    0.42
    嚕
    0.41
     quotidienne
    0.39
     ब्ले
    0.38
    Origins
    0.37
    зд
    0.37
    ్యా
    0.37
    ConformanceMode
    0.37
     numerals
    0.36
    Therates
    0.36
    POSITIVE LOGITS
     Mountains
    0.42
     Gregg
    0.38
     밝
    0.37
     Colorful
    0.35
     REP
    0.35
     Cem
    0.35
     Dism
    0.34
     sur
    0.34
     mother
    0.34
     uplifting
    0.34
    Activations Density 0.000%

    No Known Activations