© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 136167
    Prev
    Next
    INDEX
    Explanations

    specific noun after "that"

    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_37_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
    '])){
    0.41
     pt
    0.35
     हस्तक्षेप
    0.35
     Belg
    0.34
    上位
    0.34
     অনুসারে
    0.33
    pant
    0.33
     nuestros
    0.33
    त्कार
    0.33
     ){
    0.33
    POSITIVE LOGITS
    那個
    0.79
    那个
    0.78
     guy
    0.65
    那位
    0.62
    あの
    0.56
     あの
    0.55
     aquel
    0.55
    guy
    0.54
     aquele
    0.54
     той
    0.51
    Activations Density 0.002%

    No Known Activations