© 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. 201251
    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
    鄴
    0.41
     Canning
    0.39
    ято
    0.39
    鍒
    0.38
     Leeds
    0.37
     Palestine
    0.37
    Baltimore
    0.37
    लेशन
    0.36
     Thib
    0.36
     म्हट
    0.36
    POSITIVE LOGITS
     ঝ
    0.37
    rigid
    0.37
     stretched
    0.36
    Eagle
    0.35
    காற்று
    0.35
     clasific
    0.35
     ڈھ
    0.34
    heer
    0.34
    افل
    0.34
    stretched
    0.34
    Activations Density 0.000%

    No Known Activations