© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 124314
    Prev
    Next
    INDEX
    Explanations

    years

    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
     approximately
    0.64
     Approximately
    0.61
    Approximately
    0.58
     ૩
    0.54
     ८
    0.54
    approximately
    0.53
     حوالي
    0.53
    約
    0.52
     ३
    0.52
     ১৭
    0.48
    POSITIVE LOGITS
     months
    0.90
     years
    0.84
    years
    0.80
     YEARS
    0.80
     Months
    0.77
    months
    0.77
     weeks
    0.76
     jaren
    0.73
     वर्षों
    0.72
     yıll
    0.70
    Activations Density 0.099%

    No Known Activations