© 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. 45604
    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
    ﻪ
    0.53
     crimen
    0.51
     cambi
    0.46
    ﯽ
    0.46
     TypeError
    0.45
     selección
    0.44
    fetching
    0.44
     consiguió
    0.44
     trainer
    0.44
     cliché
    0.44
    POSITIVE LOGITS
    ㎢
    0.48
    avel
    0.47
     ცხ
    0.47
    ａ
    0.47
    ﹡
    0.47
     живота
    0.47
    ⓓ
    0.47
     Gogh
    0.47
     antihy
    0.47
     ਸੰ
    0.46
    Activations Density 0.000%

    No Known Activations