Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 7-GEMMASCOPE-TRANSCODER-16K
    4. 6839
    Prev
    Next
    INDEX
    Explanations

    words associated with being in a place like a home, including furniture, items, and actions

    oai_token-act-pair · gemini-2.0-flash

    Items laid out on tables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    <bos>
    -0.73
    IUrlHelper
    -0.50
    $}
    -0.47
     mergeFrom
    -0.47
    thâu
    -0.47
    ’
    -0.46
    )$}
    -0.46
    ">—
    -0.45
    CrossRef
    -0.45
    PickerController
    -0.43
    POSITIVE LOGITS
    setViewportView
    0.71
    าสตร์
    0.64
     ApiException
    0.58
    AsStream
    0.57
     tray
    0.56
    ourite
    0.56
    iterranean
    0.55
    reactstrap
    0.55
    simpleType
    0.54
    tableFuture
    0.54
    Activations Density 0.595%

    No Known Activations