© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 27180
    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_40_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
    ično
    0.42
    NonQuery
    0.40
    iki
    0.40
    slut
    0.39
    Polynomial
    0.39
    fab
    0.38
    Backspace
    0.38
     ***",
    0.38
     sains
    0.38
     technik
    0.37
    POSITIVE LOGITS
     Prosperity
    0.37
     Herr
    0.37
     NON
    0.37
     submissions
    0.36
     non
    0.35
     Non
    0.35
     birds
    0.35
     Lancaster
    0.34
     सीसी
    0.34
     غير
    0.33
    Activations Density 0.000%

    No Known Activations