© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12378
    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
    ar
    0.61
    N
    0.60
    ăl
    0.59
     iar
    0.58
    ot
    0.58
    H
    0.56
    ific
    0.54
     sounds
    0.54
     sentir
    0.54
    U
    0.53
    POSITIVE LOGITS
    ждены
    0.59
    Pham
    0.57
     озеро
    0.56
     Па
    0.55
    kola
    0.54
    слей
    0.54
    гнозы
    0.54
    зда
    0.52
    Salah
    0.52
     Makan
    0.52
    Activations Density 0.000%

    No Known Activations