© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35110
    Prev
    Next
    INDEX
    Explanations

    high-fives, high-rise, High Arctic

    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_3_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
    ك
    0.97
    k
    0.84
    l
    0.55
    كيل
    0.54
    s
    0.53
    ast
    0.53
    বে
    0.53
    的高
    0.52
    kopf
    0.52
    สูง
    0.52
    POSITIVE LOGITS
    ۰
    0.80
     sprinkled
    0.72
    ０
    0.70
    ্ু
    0.66
    꾿
    0.65
    ᱙
    0.65
     pulsation
    0.64
    ي
    0.64
     muff
    0.63
     AFD
    0.63
    Activations Density 0.010%

    No Known Activations