© 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. 10716
    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
    ాలపై
    0.50
    પુર
    0.48
    olaire
    0.48
    ст
    0.47
     unpredictable
    0.46
     स्पर्धा
    0.46
     특히
    0.46
     옳
    0.46
     высокие
    0.46
    aket
    0.46
    POSITIVE LOGITS
     \&
    0.53
    ээр
    0.52
     añade
    0.52
     zwią
    0.52
     suces
    0.51
    ך
    0.51
     suscrib
    0.50
    শ্রেণীর
    0.50
     aeropuerto
    0.50
    :":
    0.50
    Activations Density 0.000%

    No Known Activations