© 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. 54316
    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
     fiesta
    0.39
    繪
    0.38
     長袖
    0.38
    IntVar
    0.38
    واق
    0.38
     squadra
    0.37
    Hes
    0.37
    休暇
    0.37
    ·
    0.37
    SizePolicy
    0.36
    POSITIVE LOGITS
     Crem
    0.41
     sím
    0.39
     Félix
    0.38
     कॉस्ट
    0.36
     Edit
    0.36
     تل
    0.36
     ভর
    0.35
    召
    0.35
     shuffled
    0.35
     conserv
    0.34
    Activations Density 0.000%

    No Known Activations