© 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
    2. Gemma-3-27B-IT
    3. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 223326
    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_10_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
    л
    0.59
    竹
    0.47
    す
    0.47
    什么
    0.46
     gì
    0.45
     thắng
    0.44
    キ
    0.44
    止
    0.44
    ى
    0.43
    ಿಯ
    0.43
    POSITIVE LOGITS
     груп
    0.57
    uidade
    0.51
    arus
    0.50
    arnas
    0.49
    idades
    0.47
     эсеп
    0.46
    aje
    0.46
    ruik
    0.46
     Ciebie
    0.46
    ostęp
    0.46
    Activations Density 0.000%

    No Known Activations