© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174208
    Prev
    Next
    INDEX
    Explanations

    HIGH state

    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_20_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
    产业
    0.45
    Abdul
    0.41
    嵯
    0.41
    chiha
    0.40
    优惠
    0.39
     privilégi
    0.39
     एमसी
    0.38
     hydraul
    0.38
     exhilar
    0.38
    娠
    0.38
    POSITIVE LOGITS
     spielen
    0.50
     e
    0.45
     concentrates
    0.42
     aika
    0.41
    extreme
    0.41
    ische
    0.41
     समय
    0.41
     serves
    0.41
     exc
    0.40
    arrays
    0.40
    Activations Density 0.002%

    No Known Activations