© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 222001
    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_10_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
    rne
    0.51
    С
    0.49
    ne
    0.49
    ње
    0.48
     alguém
    0.48
    jpe
    0.47
    ي
    0.47
    人
    0.46
     কলেজের
    0.46
     housings
    0.46
    POSITIVE LOGITS
     già
    0.47
     chiar
    0.46
     final
    0.44
     میراتھن
    0.44
    ują
    0.43
    MONTH
    0.43
     ireo
    0.43
     mancan
    0.42
    鯊
    0.42
     Dancing
    0.42
    Activations Density 0.000%

    No Known Activations