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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8724
    Prev
    Next
    INDEX
    Explanations

    past tense forms of the verb "to work"

    oai_token-act-pair · gemini-2.0-flash

    worked

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     worked
    -1.84
    <bos>
    -1.75
     Worked
    -1.60
    worked
    -1.57
    Worked
    -1.55
     working
    -1.52
    Working
    -1.34
    working
    -1.33
     Working
    -1.30
     works
    -1.18
    POSITIVE LOGITS
     Tuch
    0.64
     DEGREE
    0.64
    itope
    0.58
     équipements
    0.55
     juger
    0.54
    Giới
    0.53
    InstanceState
    0.50
     MODER
    0.50
     tendances
    0.49
    addContainerGap
    0.48
    Activations Density 0.649%

    No Known Activations