© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 229222
    Prev
    Next
    INDEX
    Explanations

    eclipses or scientific explanations

    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
    is
    1.86
    ع
    1.74
    A
    1.41
    ت
    1.39
    é
    1.30
    ي
    1.29
    T
    1.28
    ِي
    1.23
    ות
    1.21
    يد
    1.20
    POSITIVE LOGITS
    ito
    0.92
     atau
    0.86
     gunakan
    0.85
     یا
    0.84
    ți
    0.84
    yti
    0.83
    ofi
    0.82
    irsty
    0.82
     陳
    0.81
     รถ
    0.80
    Activations Density 0.000%

    No Known Activations