© 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. 164203
    Prev
    Next
    INDEX
    Explanations

    lemongrass

    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_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
    مپ
    0.58
    م
    0.57
    تر
    0.54
    zus
    0.52
    azie
    0.52
    In
    0.50
    à
    0.50
    끊
    0.49
    But
    0.48
    ad
    0.48
    POSITIVE LOGITS
     samples
    0.61
     scares
    0.60
     б
    0.57
     bytes
    0.55
     breads
    0.55
     достаточно
    0.55
     ಇದೆ
    0.54
     сне
    0.52
     określ
    0.52
     skulls
    0.52
    Activations Density 0.000%

    No Known Activations