© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 165736
    Prev
    Next
    INDEX
    Explanations

    partial derivatives and derivatives

    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_31_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
    Æ
    0.36
     intricate
    0.34
     unravel
    0.30
     molecule
    0.29
     Barrio
    0.29
    antuan
    0.29
     customers
    0.29
    OPEN
    0.29
    BY
    0.29
    steady
    0.29
    POSITIVE LOGITS
     limitar
    0.35
     zeroth
    0.35
     BasicContainer
    0.34
    ثمان
    0.32
    تح
    0.32
    昷
    0.32
     جوان
    0.31
     بهتر
    0.31
     ограни
    0.31
     профессии
    0.31
    Activations Density 0.001%

    No Known Activations