© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 163639
    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_13_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
     patented
    0.54
     mango
    0.51
     Mango
    0.48
     Monsoon
    0.48
     Pineapple
    0.48
     l
    0.48
     missile
    0.48
     pestic
    0.47
     mathematician
    0.46
     broccoli
    0.46
    POSITIVE LOGITS
    have
    0.49
    льзова
    0.46
    そう
    0.43
    データ
    0.43
    屋
    0.43
    বে
    0.42
    require
    0.42
    рно
    0.42
    imas
    0.42
    Mas
    0.42
    Activations Density 0.000%

    No Known Activations