© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 133054
    Prev
    Next
    INDEX
    Explanations

    industrialization, heritage, capacity, city, areas

    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_6_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
    '
    1.88
    1
    1.63
    ad
    1.48
    ina
    1.38
    et
    1.34
    f
    1.34
    O
    1.34
    en
    1.31
    im
    1.31
    ↵
    1.29
    POSITIVE LOGITS
    ूटूथ
    1.09
    resTmp
    1.02
     іх
    1.01
    ឡិចត្រូ
    0.99
     بیاکت
    0.96
     паци
    0.95
     infringing
    0.95
     ил
    0.94
    ки
    0.93
    кистон
    0.93
    Activations Density 0.003%

    No Known Activations