© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43900
    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
    ak
    0.59
    old
    0.54
    3
    0.54
    if
    0.52
    는
    0.52
    Two
    0.51
    ;
    0.50
    4
    0.50
    </th>
    0.49
    2
    0.49
    POSITIVE LOGITS
     méthodique
    0.60
    眄
    0.59
    ELEASE
    0.58
    ціона
    0.57
     χρόνια
    0.56
     faço
    0.55
     reli
    0.54
    IDUAL
    0.54
    馮
    0.54
     பாண்டிய
    0.52
    Activations Density 0.000%

    No Known Activations