© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18780
    Prev
    Next
    INDEX
    Explanations

    function QuickSort

    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_15_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
    DummyView
    0.40
    舴
    0.40
    тину
    0.40
     legislate
    0.39
    निश्ड
    0.39
    哞
    0.39
     డౌ
    0.38
    噜
    0.38
    依旧
    0.37
     作为
    0.37
    POSITIVE LOGITS
    av
    0.51
    ates
    0.49
    ms
    0.49
    Base
    0.48
    ath
    0.48
    ht
    0.46
    el
    0.46
    <strong>
    0.45
    ed
    0.45
    batch
    0.44
    Activations Density 0.001%

    No Known Activations