© 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-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 9762
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to computer drives and partitioning in questions and answers

    oai_token-act-pair · gemini-2.0-flash

    Computer-related context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pokies
    -0.52
     ويكيميديا
    -0.49
    VideoCapture
    -0.48
    forKey
    -0.48
    ContentAsync
    -0.47
     Offen
    -0.47
     Copa
    -0.46
    punch
    -0.46
     Jai
    -0.46
     Annapolis
    -0.46
    POSITIVE LOGITS
     GenerationType
    0.71
    IsContent
    0.62
     виправивши
    0.58
    WithMany
    0.57
    InjectAttribute
    0.57
     متعلقه
    0.57
    AutoField
    0.56
    __(/*!
    0.55
    IVEREF
    0.55
     kaynağından
    0.54
    Activations Density 1.507%

    No Known Activations