© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 80738
    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_31_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
     Kommentar
    0.45
     Chow
    0.37
     Finished
    0.37
     Eriksson
    0.37
     Modell
    0.36
     राजेंद्र
    0.36
    ೇ
    0.35
    뀐
    0.35
     واقعہ
    0.35
     Official
    0.35
    POSITIVE LOGITS
    ในปี
    0.36
    itions
    0.36
    径
    0.35
     dhad
    0.35
    क्राइब
    0.34
     ১৯৯
    0.34
    -*
    0.34
    ждению
    0.34
    ＊
    0.34
     otak
    0.34
    Activations Density 0.000%

    No Known Activations