© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 132248
    Prev
    Next
    INDEX
    Explanations

    piece about

    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
    ↵
    1.45
    ल
    1.24
     to
    1.16
    า
    1.08
    я
    0.96
    ia
    0.96
    INE
    0.94
    ปี
    0.92
    .
    0.92
    ล
    0.90
    POSITIVE LOGITS
    s
    1.60
    وي
    1.23
    O
    1.22
     تاريخ
    1.16
    ي
    1.16
     مي
    1.16
     ممكن
    1.16
     جديد
    1.13
     مؤرشف
    1.13
    P
    1.11
    Activations Density 0.002%

    No Known Activations