© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1139
    Prev
    Next
    INDEX
    Explanations

    rounding to two decimal places

    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
    To
    0.95
     To
    0.92
    to
    0.81
    到
    0.70
     to
    0.65
     至
    0.65
     إلى
    0.64
     TO
    0.59
     الى
    0.59
    至
    0.59
    POSITIVE LOGITS
     Zwei
    0.62
     two
    0.61
     двух
    0.60
     zwei
    0.60
     deux
    0.59
     två
    0.55
     δύο
    0.55
     دو
    0.54
     দুই
    0.54
     dvou
    0.54
    Activations Density 0.014%

    No Known Activations