© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13106
    Prev
    Next
    INDEX
    Explanations

    review or instruction about

    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
    鸴
    0.36
     Mora
    0.28
     प्रशिक्
    0.28
    Jenis
    0.28
    화
    0.28
     ಸಂದ
    0.27
    dyna
    0.27
    قام
    0.27
    䛊
    0.27
    acu
    0.26
    POSITIVE LOGITS
    ordia
    0.29
     planet
    0.28
    юсь
    0.27
    ськ
    0.27
    iales
    0.27
    anele
    0.27
    uchen
    0.27
     noqa
    0.27
     Laundry
    0.27
    uces
    0.27
    Activations Density 0.138%

    No Known Activations