© 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. 3257
    Prev
    Next
    INDEX
    Explanations

    late 2023 / early 2024

    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
     autumn
    0.57
     Autumn
    0.54
    Autumn
    0.50
     autumnal
    0.47
    秋
    0.46
    autumn
    0.45
     Herbst
    0.45
     осень
    0.43
     otoño
    0.43
    Third
    0.41
    POSITIVE LOGITS
     quarter
    1.06
     Quarter
    0.93
    quarter
    0.85
    Quarter
    0.82
     quarters
    0.75
     кварта
    0.71
     начале
    0.66
     Quarterly
    0.66
     ¼
    0.65
     trimestre
    0.64
    Activations Density 0.040%

    No Known Activations