© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10974
    Prev
    Next
    INDEX
    Explanations

    the past tense of the verb "work"

    oai_token-act-pair · gemini-2.0-flash

    worked

    np_max-act · gemini-2.0-flash

    ▁worked

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    脚注の使い方
    -0.83
    DockStyle
    -0.81
     متعلقه
    -0.63
     تانيه
    -0.62
    PhysRevD
    -0.62
    seam
    -0.60
    hysema
    -0.59
    setupUi
    -0.59
     jsPsych
    -0.59
    ousands
    -0.57
    POSITIVE LOGITS
    AndroidJUnit
    0.60
     resourceCulture
    0.55
     Roskov
    0.54
    DeleteCommand
    0.54
    COHOL
    0.50
    FXMLLoader
    0.49
    (!__
    0.48
     erfre
    0.48
     transférez
    0.47
    PyTuple
    0.47
    Activations Density 0.670%

    No Known Activations