© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 213783
    Prev
    Next
    INDEX
    Explanations

    North Island or Auckland

    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_16_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
     vrijeme
    0.49
    飏
    0.45
     up
    0.45
     nakon
    0.44
     lm
    0.42
     morte
    0.41
     commemorate
    0.41
     servizi
    0.41
     hurdles
    0.40
     měl
    0.40
    POSITIVE LOGITS
    ما
    0.49
    م
    0.47
    de
    0.46
    mə
    0.45
    نا
    0.44
    முடிய
    0.41
    tea
    0.41
    tomato
    0.41
    म
    0.39
    do
    0.39
    Activations Density 0.003%

    No Known Activations