© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89009
    Prev
    Next
    INDEX
    Explanations

    stereoscopic vision / viewing

    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
     can
    1.04
     was
    0.82
    5
    0.80
    (
    0.78
    ized
    0.76
    1
    0.73
    }$
    0.71
     be
    0.70
     we
    0.70
     you
    0.69
    POSITIVE LOGITS
     Ин
    0.84
     Та
    0.77
    िफ्ट
    0.73
     Органи
    0.73
     Са
    0.73
     Ор
    0.72
     परामर्श
    0.72
    لیس
    0.71
    ᇁ
    0.71
    یا
    0.71
    Activations Density 0.000%

    No Known Activations