© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12878
    Prev
    Next
    INDEX
    Explanations

    the word "callback" inside of code snippets

    oai_token-act-pair · gemini-2.0-flash

    callback

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    L
    -0.76
    P
    -0.75
    S
    -0.72
    nd
    -0.71
    est
    -0.70
    ner
    -0.69
    I
    -0.69
    s
    -0.66
     (
    -0.66
    l
    -0.66
    POSITIVE LOGITS
    ViewFeatures
    1.27
     Roskov
    1.16
     AssemblyCulture
    1.14
    UrlResolution
    1.13
    IUrlHelper
    1.09
    ########.
    1.09
     HasFactory
    1.06
     Meksiku
    1.05
    contentLoaded
    1.03
     typelib
    1.03
    Activations Density 2.798%

    No Known Activations