© 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. 29936
    Prev
    Next
    INDEX
    Explanations

    asymptomatic/symptomatic

    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
     लटका
    0.39
     deixou
    0.37
    calendar
    0.36
    囝
    0.36
     terb
    0.36
    ոչ
    0.35
    DatePicker
    0.35
    糟糕
    0.34
    ၻ
    0.34
     फोटो
    0.34
    POSITIVE LOGITS
     asymptomatic
    2.42
     asympt
    2.41
     asymptotic
    2.31
     asymptotically
    2.06
     asymptotics
    2.02
     asymptote
    1.96
     asylum
    1.83
    ympt
    1.74
     Asylum
    1.71
     symptomatic
    1.59
    Activations Density 0.076%

    No Known Activations