© 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. 38949
    Prev
    Next
    INDEX
    Explanations

    Wu-Tang Clan, Wukang Road, Wu Sangui

    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
    üğünüz
    0.64
    ė
    0.59
    >(&
    0.59
     racquet
    0.54
     süre
    0.54
     činjen
    0.54
     смогли
    0.53
    izzes
    0.53
     ช่วย
    0.53
     другую
    0.53
    POSITIVE LOGITS
    a
    1.23
    t
    1.20
    i
    1.05
    ي
    0.93
    e
    0.89
    י
    0.89
    া
    0.88
    u
    0.87
    ه
    0.84
    an
    0.82
    Activations Density 0.000%

    No Known Activations