© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 92977
    Prev
    Next
    INDEX
    Explanations

    clashing, clunky, clutching

    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_11_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
    ভাবে
    0.60
     conexion
    0.56
     conversación
    0.55
     configuración
    0.55
     gaman
    0.53
    BRAS
    0.52
     cơn
    0.52
    <0x80>
    0.52
     colaboración
    0.52
     decisión
    0.51
    POSITIVE LOGITS
    Y
    0.77
    v
    0.76
    z
    0.73
    0.65
     Каждый
    0.63
    anyone
    0.63
     Що
    0.62
    ushes
    0.61
    umm
    0.60
     Hiện
    0.60
    Activations Density 0.004%

    No Known Activations