© 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. 46713
    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
    (
    0.50
     listener
    0.49
    {})
    0.49
     watt
    0.47
     wys
    0.45
    لاه
    0.44
     mä
    0.43
     WAT
    0.43
     pq
    0.43
     virulence
    0.43
    POSITIVE LOGITS
    have
    0.58
    am
    0.57
    䝬
    0.55
     similaire
    0.55
    rett
    0.55
    crim
    0.55
    un
    0.54
    replace
    0.53
    arbe
    0.53
    acted
    0.53
    Activations Density 0.000%

    No Known Activations