© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 34183
    Prev
    Next
    INDEX
    Explanations

    crimson colors

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     SHEET
    0.39
    Nx
    0.39
     Sheets
    0.38
     स्वतः
    0.38
     Beet
    0.37
    鈾
    0.37
    華
    0.37
    Sugar
    0.36
     বিএন
    0.36
     स्
    0.36
    POSITIVE LOGITS
     k
    0.69
     Kerm
    0.60
     coc
    0.52
    Coc
    0.45
    coc
    0.44
     क
    0.43
     cocker
    0.43
     ك
    0.42
    Kerry
    0.41
    𝐜
    0.41
    Activations Density 0.013%

    No Known Activations