© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 201628
    Prev
    Next
    INDEX
    Explanations

    crossed their legs/arms/path/bridge/sea

    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_6_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
    त
    1.07
    a
    1.02
    ت
    1.00
     задачи
    0.93
    amental
    0.88
    arı
    0.88
    ৯
    0.86
     ínt
    0.86
    ्ट
    0.85
     теа
    0.84
    POSITIVE LOGITS
    N
    0.91
    า
    0.88
    z
    0.86
    л
    0.84
    ار
    0.83
    ায়
    0.83
    2
    0.82
    of
    0.80
    ुल्लाह
    0.80
    ين
    0.79
    Activations Density 0.001%

    No Known Activations