© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 131932
    Prev
    Next
    INDEX
    Explanations

    recognize all

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_6_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
     in
    1.11
     at
    1.11
    ch
    0.96
    ↵↵
    0.95
    ק
    0.95
    các
    0.90
     разби
    0.89
     aquest
    0.89
     ocurre
    0.89
     parla
    0.89
    POSITIVE LOGITS
    들이
    1.12
    와의
    1.00
    O
    0.95
    3
    0.95
    EY
    0.91
    ów
    0.87
    0
    0.86
    IES
    0.84
    Whitespace
    0.84
    ul
    0.82
    Activations Density 0.003%

    No Known Activations