© 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. 12681
    Prev
    Next
    INDEX
    Explanations

    the word 'led' or phrases where something leads to something else (causation)

    oai_token-act-pair · gemini-2.0-flash

    led

    np_max-act · gemini-2.0-flash
    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
     led
    -0.84
    tvguidetime
    -0.73
     nahilalakip
    -0.68
    StoryboardSegue
    -0.60
    Revenir
    -0.60
     <<<<<<<<<<<<<<
    -0.59
    PRWEB
    -0.59
     comigo
    -0.58
    WriteBarrier
    -0.58
    ionView
    -0.58
    POSITIVE LOGITS
    <bos>
    1.14
    URLException
    0.54
     lead
    0.52
    狀
    0.50
     draw
    0.50
     build
    0.49
    UnknownFieldSet
    0.49
     culturel
    0.48
    โท
    0.48
    ходе
    0.48
    Activations Density 0.418%

    No Known Activations