© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31455
    Prev
    Next
    INDEX
    Explanations

    nuclear topics

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    核
    3.36
     nuclear
    3.33
    Nuclear
    3.14
     Nuclear
    3.13
    nuclear
    3.05
     nucle
    3.03
     핵
    2.89
     Nucle
    2.88
    Nucle
    2.88
     NUCLEAR
    2.84
    POSITIVE LOGITS
     dj
    0.39
    crossentropy
    0.39
     gypsy
    0.38
    鏝
    0.37
     david
    0.36
     อาจารย์
    0.36
     BOU
    0.35
     bots
    0.35
     barbers
    0.35
     gutters
    0.35
    Activations Density 0.032%

    No Known Activations