© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 145900
    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_0_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
    扰
    0.49
     cárc
    0.47
    形状
    0.47
    .’
    0.45
     కార్య
    0.45
    )}$-
    0.43
     parado
    0.42
    坵
    0.42
    ños
    0.42
    破損
    0.42
    POSITIVE LOGITS
    Мы
    0.54
    Ве
    0.53
     putern
    0.47
    лянчук
    0.46
    Бе
    0.46
    Д
    0.45
     en
    0.45
    ல்
    0.45
    ўцаў
    0.44
    ன்
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.