© 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. 45467
    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
    ος
    0.51
    chées
    0.51
     داستان
    0.50
    Stories
    0.49
    ющимся
    0.48
    ertown
    0.48
    <
    0.47
    зо
    0.47
    ας
    0.46
    LocalizedString
    0.46
    POSITIVE LOGITS
     nCmd
    0.57
     devono
    0.53
     tain
    0.53
     ullam
    0.52
     cómodo
    0.52
     tailed
    0.52
    inine
    0.51
     বিনা
    0.51
     degrading
    0.51
     první
    0.51
    Activations Density 0.000%

    No Known Activations