© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12134
    Prev
    Next
    INDEX
    Explanations

    instances of people "working" on something, along with related terms like research or teamwork.

    oai_token-act-pair · gemini-2.0-flash

    working

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     working
    -2.59
    Working
    -2.39
    working
    -2.30
     Working
    -2.28
     WORKING
    -2.22
    WORKING
    -2.08
     worked
    -1.44
    worked
    -1.22
     trabajando
    -1.20
     trabalhando
    -1.16
    POSITIVE LOGITS
    astronomie
    0.63
    lapsingToolbar
    0.60
    }{*}{
    0.58
     HasFactory
    0.58
    URLException
    0.57
    IVEREF
    0.54
     ComVisible
    0.52
    ngdoc
    0.51
    mainen
    0.51
     Riproduzione
    0.51
    Activations Density 5.658%

    No Known Activations