© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246966
    Prev
    Next
    INDEX
    Explanations

    image `alt` attribute

    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_40_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
    親
    0.40
     ’
    0.39
     \"
    0.38
    fs
    0.38
    fix
    0.38
    text
    0.37
    words
    0.37
     woorden
    0.37
     kosten
    0.36
     Kosten
    0.36
    POSITIVE LOGITS
    骜
    0.43
     externo
    0.39
     Shaun
    0.39
    圖像
    0.38
     зобра
    0.38
     pictorial
    0.37
     pictured
    0.37
    ══
    0.37
     ол
    0.37
     зовніш
    0.37
    Activations Density 0.001%

    No Known Activations