© 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
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2117
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with causality or reasoning

    oai_token-act-pair · gemini-2.0-flash

    explanations

    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
    CloseOperation
    -0.63
    InjectAttribute
    -0.59
     Taktlose
    -0.57
     validamos
    -0.52
    writeFieldEnd
    -0.52
    openSession
    -0.52
    хьтан
    -0.50
    AutoScale
    -0.49
    المناصب
    -0.49
     manquer
    -0.49
    POSITIVE LOGITS
    HtmlAttribute
    0.62
    ReusableCell
    0.61
     purpoſe
    0.56
    Legende
    0.53
     EconPapers
    0.51
    ipients
    0.50
    Rhestr
    0.48
    IPAC
    0.48
    uktion
    0.47
    ETER
    0.46
    Activations Density 3.798%

    No Known Activations