© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15709
    Prev
    Next
    INDEX
    Explanations

    the word "context" and related API calls in code

    oai_token-act-pair · gemini-2.0-flash

    context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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>
    -1.39
     Monfieur
    -0.97
     nahilalakip
    -0.94
     myſelf
    -0.90
     Jefus
    -0.88
     Cæsar
    -0.85
     Theſe
    -0.84
     autorytatywna
    -0.84
     Efq
    -0.84
     whoſe
    -0.80
    POSITIVE LOGITS
     تضيفلها
    0.55
     nevertheless
    0.51
     Nevertheless
    0.51
     Jovi
    0.49
    inex
    0.49
     ط
    0.49
    ISY
    0.49
    FirstResponder
    0.47
    linkedin
    0.47
    yard
    0.47
    Activations Density 1.149%

    No Known Activations