© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59719
    Prev
    Next
    INDEX
    Explanations

    REQUIRED

    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_2_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
    5
    0.92
    ربي
    0.82
    О
    0.81
    정이
    0.80
     commerciaux
    0.76
     disponibles
    0.74
    ふる
    0.73
     которому
    0.72
     Australie
    0.72
    に使
    0.71
    POSITIVE LOGITS
    in
    1.09
    ם
    1.02
    ן
    0.95
    า
    0.90
    ع
    0.85
    ัน
    0.83
    g
    0.82
    n
    0.79
    k
    0.79
     be
    0.79
    Activations Density 0.004%

    No Known Activations