© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 207760
    Prev
    Next
    INDEX
    Explanations

    size is small

    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_10_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
    Π
    0.44
     neckline
    0.44
    总
    0.44
     Wunder
    0.41
    Spectral
    0.41
    Multiply
    0.40
    内地
    0.40
    手中
    0.40
    Distrib
    0.39
    各类
    0.38
    POSITIVE LOGITS
    ierten
    0.58
    anda
    0.54
    ugeot
    0.52
    ";
    0.52
    ız
    0.52
    loss
    0.52
    food
    0.52
     ánh
    0.51
    đi
    0.51
    dbThoughtData
    0.51
    Activations Density 0.000%

    No Known Activations