© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170682
    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_20_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
    ानंतर
    0.45
    較
    0.42
    ária
    0.42
     حالت
    0.41
    দেবের
    0.40
     ];
    0.40
     שנ
    0.39
     northward
    0.39
     колеба
    0.39
     بث
    0.39
    POSITIVE LOGITS
    r
    0.58
    wot
    0.56
    𝐰
    0.54
    Ң
    0.51
    ങ്കി
    0.48
    ᕼ
    0.48
    const
    0.47
    줄
    0.47
    arzy
    0.47
    ूथ
    0.47
    Activations Density 0.000%

    No Known Activations