© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10774
    Prev
    Next
    INDEX
    Explanations

    the word "work" followed or preceeded by other words

    oai_token-act-pair · gemini-2.0-flash

    work

    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
    <bos>
    -1.59
     work
    -1.27
     worked
    -1.18
    Work
    -1.16
    work
    -1.12
     Work
    -1.09
     '\\;'
    -1.08
     Worked
    -1.07
     WORK
    -1.05
    worked
    -0.99
    POSITIVE LOGITS
    principalTable
    0.46
     nào
    0.45
     Retire
    0.44
    مست
    0.42
    ộn
    0.40
     lục
    0.39
     thiết
    0.39
     Un
    0.39
    seca
    0.39
    يتر
    0.39
    Activations Density 1.867%

    No Known Activations