© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36449
    Prev
    Next
    INDEX
    Explanations

    testing tools and load testing

    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
    ждении
    0.25
    sPath
    0.24
     Barcl
    0.23
    ቻል
    0.23
    mAvailable
    0.22
    릿
    0.22
     preservative
    0.22
    FProperties
    0.22
    тура
    0.22
     JPanel
    0.22
    POSITIVE LOGITS
    gulpfile
    0.20
     избе
    0.20
     meist
    0.20
    ng
    0.20
    </em>
    0.20
     عادة
    0.20
    વાદ
    0.20
     счита
    0.19
     позна
    0.19
     கணி
    0.19
    Activations Density 0.008%

    No Known Activations