© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 505
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to scientific research and publications

    oai_token-act-pair · gemini-2.0-flash

    scientific research/publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     research
    -0.61
    期刊论文
    -0.57
     papers
    -0.56
    arXiv
    -0.54
    论文
    -0.54
     scientific
    -0.53
    paper
    -0.52
    참고
    -0.51
     researchers
    -0.50
    jspx
    -0.50
    POSITIVE LOGITS
    enerys
    0.58
     nač
    0.57
     lenker
    0.57
     متعلقه
    0.56
    WAUKEE
    0.54
    KEYCODE
    0.54
    GIVEREF
    0.54
     Numerology
    0.54
     arşivlendi
    0.53
    LLocation
    0.53
    Activations Density 3.899%

    No Known Activations