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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15016
    Prev
    Next
    INDEX
    Explanations

    words related to expenditure of effort, politeness, or lengths of things, including the expression to "take time"

    oai_token-act-pair · gemini-2.0-flash

    resource expenditure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ))).
    -0.68
     Италијани
    -0.66
    '],'
    -0.65
    ']]
    -0.63
    "]]
    -0.63
     verrez
    -0.62
    ']=='
    -0.61
    '));
    -0.60
    ()?;
    -0.60
    verwijspagina
    -0.59
    POSITIVE LOGITS
     BoxFit
    0.61
    migrationBuilder
    0.53
     useStyles
    0.52
    setupUi
    0.52
    DataSetChanged
    0.50
    KommentareTeilen
    0.50
    ējās
    0.46
     vPvB
    0.45
    getWriter
    0.45
     onPostExecute
    0.45
    Activations Density 0.731%

    No Known Activations