© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 50552
    Prev
    Next
    INDEX
    Explanations

    grab or grabs

    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_30_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
    庐
    0.41
    Simpson
    0.39
     Simpson
    0.38
    Limit
    0.38
    ၉
    0.37
    தந்திர
    0.37
     منف
    0.37
    Land
    0.36
    潛行
    0.36
     rộng
    0.36
    POSITIVE LOGITS
     grabs
    0.89
     grab
    0.85
     Grab
    0.85
     grabbed
    0.84
    Grab
    0.82
     grabbing
    0.82
    grab
    0.75
    grabbing
    0.66
     seize
    0.66
    抓
    0.65
    Activations Density 0.013%

    No Known Activations