© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123355
    Prev
    Next
    INDEX
    Explanations

    SGD (Stochastic Gradient Descent) or Singapore Dollars

    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_3_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
    ्स
    0.89
    ер
    0.84
    л
    0.84
    ים
    0.76
     термин
    0.76
    ларга
    0.74
     будто
    0.74
    oea
    0.73
     آدمی
    0.72
    ות
    0.71
    POSITIVE LOGITS
    '
    1.14
    O
    0.82
    U
    0.81
    L
    0.81
    S
    0.80
     to
    0.79
    IA
    0.79
    N
    0.78
    !
    0.76
    Library
    0.73
    Activations Density 0.004%

    No Known Activations