© 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. 202083
    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
     form
    0.38
     incur
    0.38
    احنا
    0.37
    冊
    0.37
     भु
    0.36
     Mix
    0.36
     प्रूव
    0.36
     مبلغ
    0.35
     mix
    0.35
    ména
    0.35
    POSITIVE LOGITS
     ಒಂದ
    0.40
     refriger
    0.39
    ^{+}\
    0.37
     refrigerant
    0.37
     refrigerator
    0.36
     grayish
    0.36
    Refrigerator
    0.36
     ऑक्सी
    0.36
     refrigeration
    0.36
     ಇದಕ್ಕೆ
    0.36
    Activations Density 0.000%

    No Known Activations