© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 206139
    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
    Flat
    0.37
    flat
    0.37
     अध्या
    0.36
    ɲ
    0.36
    teryx
    0.36
     سمع
    0.36
     ambil
    0.35
    rsfs
    0.35
    ㅅ
    0.35
    lay
    0.35
    POSITIVE LOGITS
     calibr
    0.41
     clearing
    0.39
     ."
    0.38
    卋
    0.38
    機會
    0.37
     hoisted
    0.37
     फं
    0.37
    セイ
    0.37
     handbags
    0.36
     اکبر
    0.36
    Activations Density 0.000%

    No Known Activations