© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 197594
    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_4_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
    i
    0.63
    h
    0.51
    Promotion
    0.50
     suggested
    0.49
     น้อย
    0.47
     Promotion
    0.47
     कमेटी
    0.47
    Reflection
    0.46
    promotion
    0.46
    Suggested
    0.46
    POSITIVE LOGITS
    盻
    0.51
    تباينه
    0.50
     Nası
    0.49
     insures
    0.48
    囡
    0.48
     narr
    0.48
     hbox
    0.47
    加入
    0.46
     характери
    0.46
     personagens
    0.46
    Activations Density 0.000%

    No Known Activations