© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 2377
    Prev
    Next
    INDEX
    Explanations

    files and paths

    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_40_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
     Attorneys
    0.41
     oude
    0.39
     karbon
    0.38
     immagini
    0.38
     ফর্ম
    0.38
     форма
    0.37
    nemonic
    0.37
    髂
    0.37
    Attorney
    0.37
    पीड़
    0.36
    POSITIVE LOGITS
    file
    0.78
     file
    0.77
    ファイル
    0.71
    ファイルの
    0.70
    文件
    0.68
    File
    0.65
     files
    0.65
     파일
    0.64
    文件的
    0.64
     File
    0.64
    Activations Density 0.107%

    No Known Activations