© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13237
    Prev
    Next
    INDEX
    Explanations

    narrow down

    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_13_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
    봇
    0.56
     disruptions
    0.48
    o
    0.47
     invo
    0.47
     raft
    0.46
    缺乏
    0.46
     pathways
    0.44
    رز
    0.44
     gatherings
    0.44
     rez
    0.44
    POSITIVE LOGITS
     Klang
    0.59
    ри
    0.56
    ranked
    0.56
    ן
    0.56
    лишком
    0.53
    .),
    0.52
     കൂടുതൽ
    0.52
     khúc
    0.51
    ی
    0.51
    的用户
    0.50
    Activations Density 0.012%

    No Known Activations