© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18629
    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_15_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
    LookAndFeel
    0.10
    ✡
    0.09
    اء
    0.09
    ա
    0.09
    าราง
    0.09
    า
    0.09
    Optimization
    0.09
    อาหาร
    0.09
    িপ
    0.09
    اا
    0.09
    POSITIVE LOGITS
     instruction
    0.12
     `'\\
    0.11
     nine
    0.11
     convicts
    0.11
     instructs
    0.11
     evicted
    0.11
     শিক্ষার্থী
    0.11
     escaped
    0.11
     выну
    0.10
     sepol
    0.10
    Activations Density 0.000%

    No Known Activations