© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 34437
    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_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
     ন্যায
    0.38
     обосно
    0.38
     RasterModelGrid
    0.38
     presenta
    0.38
     ਐ
    0.38
     оправ
    0.38
     massless
    0.37
     molle
    0.37
    原始
    0.36
    娑
    0.36
    POSITIVE LOGITS
     Knee
    0.38
     Destroy
    0.37
     ধাতু
    0.36
     Loy
    0.35
     Gio
    0.35
     ধ্বংস
    0.34
     residuos
    0.34
     ruined
    0.34
    forderung
    0.34
     SCAN
    0.34
    Activations Density 0.000%

    No Known Activations