© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 15356
    Prev
    Next
    INDEX
    Explanations

    code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_34_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
     останов
    0.37
     Arx
    0.34
    enchymal
    0.34
     सरी
    0.33
    醃
    0.33
    unnels
    0.33
     बिन
    0.32
     増
    0.32
     stopped
    0.32
     ',
    0.32
    POSITIVE LOGITS
    Tul
    0.36
     demo
    0.36
    StrictMode
    0.35
     mats
    0.35
     uplift
    0.35
     biological
    0.35
     péld
    0.35
     voorbeeld
    0.34
     firsthand
    0.34
    䅡
    0.34
    Activations Density 0.013%

    No Known Activations