© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 12404
    Prev
    Next
    INDEX
    Explanations

    the javascript keyword 'typeof'

    oai_token-act-pair · gemini-2.0-flash

    typeof

    np_max-act · gemini-2.0-flash

    typeof

    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_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
    %)$
    -0.81
    ://"
    -0.72
    encies
    -0.69
     Waray
    -0.69
    ."));
    -0.65
     stress
    -0.65
    %");
    -0.65
    %";
    -0.65
    ("]");
    -0.64
    ')):
    -0.64
    POSITIVE LOGITS
    <bos>
    0.86
     opérateur
    0.63
    AutoScaleMode
    0.62
     frattempo
    0.54
     vellum
    0.54
    ंदीखरीदारी
    0.54
     sandstones
    0.53
    :✨
    0.52
     deserto
    0.52
     resection
    0.52
    Activations Density 1.196%

    No Known Activations