© 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. 90714
    Prev
    Next
    INDEX
    Explanations

    moment matching

    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
    리로
    0.64
     क्षण
    0.63
    رى
    0.63
    م
    0.63
     मुख्यमंत्री
    0.61
     организация
    0.61
     gráficos
    0.61
     tathapi
    0.61
     순간
    0.61
    <0x0D>
    0.60
    POSITIVE LOGITS
    id
    0.78
    idae
    0.70
    ках
    0.69
    wl
    0.69
     layers
    0.64
     surfaces
    0.64
    \
    0.63
    xh
    0.63
     r
    0.61
    eth
    0.61
    Activations Density 0.005%

    No Known Activations