© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37489
    Prev
    Next
    INDEX
    Explanations

    Bramblefoot, Bramblewood, bramble patch

    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_11_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
    ،
    0.56
     t
    0.51
    olding
    0.51
     or
    0.50
    ={
    0.48
    Ancient
    0.48
    lerin
    0.47
     leaning
    0.47
    gement
    0.47
    usions
    0.47
    POSITIVE LOGITS
     développe
    0.53
     sólo
    0.52
     Ú
    0.52
    ক্ষম
    0.51
     eléctrica
    0.49
     étab
    0.49
     quantité
    0.49
     создает
    0.48
     edilir
    0.48
     détermine
    0.47
    Activations Density 0.000%

    No Known Activations