© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7507
    Prev
    Next
    INDEX
    Explanations

    the word "fire", especially in contexts related to firefighting, fire stations, or fire canons/hoses.

    oai_token-act-pair · gemini-2.0-flash

    fire

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    MIME
    -0.52
     externi
    -0.49
    Geplaatst
    -0.49
     Schweitzer
    -0.48
    URO
    -0.44
    uro
    -0.43
     useStyles
    -0.43
    jelder
    -0.43
    IsMutable
    -0.42
    GetInt
    -0.41
    POSITIVE LOGITS
    tagHelperRunner
    0.82
    httphttps
    0.74
     autorytatywna
    0.74
    HtmlAttribute
    0.71
     nakalista
    0.71
     ExecuteAsync
    0.64
    PYX
    0.57
     PackageManager
    0.57
    IsPostBack
    0.57
    sizeCache
    0.56
    Activations Density 1.521%

    No Known Activations