© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 90688
    Prev
    Next
    INDEX
    Explanations

    stand up or stand desk

    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_3_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
    o
    0.81
    のは
    0.72
    i
    0.67
    ﺎ
    0.62
     pirm
    0.60
    aquest
    0.60
     setan
    0.59
    같이
    0.59
     aguda
    0.59
     ublox
    0.59
    POSITIVE LOGITS
     to
    1.03
    𝐧
    0.71
    ص
    0.68
    تم
    0.66
    ites
    0.64
    𝐫
    0.64
    ج
    0.64
    هم
    0.61
    شي
    0.61
    سو
    0.61
    Activations Density 0.000%

    No Known Activations