© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141640
    Prev
    Next
    INDEX
    Explanations

    preserved, heritage, registration, batch, storage

    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_12_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
     👀
    0.49
     Telegram
    0.48
     Lian
    0.48
     Brazilian
    0.47
     Shopify
    0.47
    回事
    0.47
     Dominican
    0.46
    LightTheme
    0.46
     Peruvian
    0.46
     Lans
    0.46
    POSITIVE LOGITS
     bună
    0.59
    ّد
    0.55
     tragedies
    0.54
    ле
    0.51
     coerc
    0.51
    構
    0.50
    德
    0.49
    チ
    0.49
     concaten
    0.48
     crevices
    0.48
    Activations Density 0.002%

    No Known Activations