© 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. 135234
    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
    ())));
    0.41
     EPA
    0.41
    みを
    0.38
    දිය
    0.37
     المقدس
    0.36
    ೃಹ
    0.36
    ρέ
    0.35
     இதை
    0.35
    ဟာ
    0.35
     Legendre
    0.35
    POSITIVE LOGITS
     будете
    0.42
    䈤
    0.41
    WordArray
    0.39
     mason
    0.39
     courses
    0.38
     perspiration
    0.38
     겨
    0.38
    nament
    0.37
    ortium
    0.37
     सेशन
    0.37
    Activations Density 0.000%

    No Known Activations