© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 182966
    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_29_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
    这段
    0.40
    снов
    0.39
     эти
    0.38
     இந்த
    0.38
    缬
    0.38
    нести
    0.38
     crown
    0.37
    战争
    0.37
    menubar
    0.37
    னின்
    0.37
    POSITIVE LOGITS
    inaldo
    0.38
     угодно
    0.38
    ꜜ
    0.38
    .]
    0.38
    atly
    0.36
    Nft
    0.35
    🔡
    0.35
    ﭥ
    0.35
    hxx
    0.34
     milion
    0.34
    Activations Density 0.000%

    No Known Activations