© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 22496
    Prev
    Next
    INDEX
    Explanations

    6

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    olybdenum
    0.37
    صفر
    0.36
    っていく
    0.35
    图书馆
    0.35
    蝙
    0.34
    的管理
    0.34
    図書館
    0.34
     برج
    0.33
    ୫
    0.33
    Sodium
    0.33
    POSITIVE LOGITS
     December
    0.52
     good
    0.49
     декабря
    0.42
     december
    0.42
     ator
    0.40
     dobr
    0.40
    icions
    0.39
     November
    0.38
     Christmas
    0.38
     loca
    0.38
    Activations Density 0.002%

    No Known Activations