© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 105957
    Prev
    Next
    INDEX
    Explanations

    "That's right" followed by continuation

    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_1_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
    <0x0D>
    1.35
    يل
    0.97
     đó
    0.92
     powied
    0.88
     взя
    0.88
    ２
    0.85
    "})
    0.85
    ปี
    0.84
    一
    0.83
    ブ
    0.83
    POSITIVE LOGITS
    س
    1.05
    in
    1.03
    ak
    0.93
    า
    0.92
    ors
    0.91
    ang
    0.90
    ia
    0.88
    ない
    0.87
    im
    0.85
    oli
    0.85
    Activations Density 0.003%

    No Known Activations