© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 98943
    Prev
    Next
    INDEX
    Explanations

    "Is your name Google? Because you have everything I've been searching for."

    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_16_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
    セ
    0.56
    পরিস
    0.54
    schools
    0.53
     Bankers
    0.53
    Người
    0.52
    Businesses
    0.52
    ᱞ
    0.52
    行的
    0.52
    وران
    0.52
     sulphuric
    0.52
    POSITIVE LOGITS
     §
    0.54
     evokes
    0.48
     n
    0.47
     insbesondere
    0.45
     разум
    0.44
     ​​
    0.43
     entrusted
    0.42
     embodies
    0.42
     opět
    0.42
     justifies
    0.42
    Activations Density 0.000%

    No Known Activations