© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 216394
    Prev
    Next
    INDEX
    Explanations

    HTML table cell

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     affront
    0.44
     Kolmogorov
    0.43
    ǒ
    0.40
     pij
    0.40
     hecho
    0.39
     mó
    0.39
     Veracruz
    0.39
    ሦ
    0.39
    Listing
    0.38
     पप्पू
    0.38
    POSITIVE LOGITS
     TD
    0.62
    TD
    0.54
     TC
    0.47
     TCM
    0.47
     td
    0.45
    TC
    0.45
     tc
    0.44
     TF
    0.44
     TDs
    0.44
     TDC
    0.43
    Activations Density 0.001%

    No Known Activations