© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 123421
    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_37_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
    laat
    0.41
    autes
    0.41
    फिल
    0.38
    鸡蛋
    0.38
     Blume
    0.38
    즙
    0.37
    APK
    0.36
     eggs
    0.36
    KES
    0.36
    FEED
    0.36
    POSITIVE LOGITS
    ャ
    0.40
     Guan
    0.39
     elicited
    0.38
     expelled
    0.36
     STL
    0.36
     Oz
    0.35
    erful
    0.35
     membranes
    0.34
     ಕ್ಷೇತ್ರ
    0.34
    oxel
    0.34
    Activations Density 0.000%

    No Known Activations