© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 161950
    Prev
    Next
    INDEX
    Explanations

    foreign names or phrases following punctuation

    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_31_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
     coinciding
    0.38
    ဆ
    0.38
    ницу
    0.37
    נון
    0.36
     രീതി
    0.34
     insensitive
    0.34
    Ŵ
    0.34
    Near
    0.34
    Common
    0.33
     Near
    0.33
    POSITIVE LOGITS
     occupé
    0.47
     Bajo
    0.45
    
    0.39
    俱乐
    0.39
    多元
    0.38
     CFRP
    0.38
    धिकार
    0.37
     коже
    0.37
     quirúrg
    0.37
    科学院
    0.36
    Activations Density 0.000%

    No Known Activations