© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5078
    Prev
    Next
    INDEX
    Explanations

    the word "margin," especially in a financial context

    oai_token-act-pair · gemini-2.0-flash

    margin

    np_max-act · gemini-2.0-flash

    margin

    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
    -
    -0.88
    “
    -0.85
    <em>
    -0.84
    <strong>
    -0.82
    "
    -0.80
     
    -0.77
    .
    -0.77
    <bos>
    -0.76
    ↵
    -0.71
    by
    -0.71
    POSITIVE LOGITS
    SBATCH
    1.59
    BibitemShut
    1.53
    queryInterface
    1.51
    bibfield
    1.41
    bibinfo
    1.41
    ^(@)
    1.40
     Réponses
    1.38
    PerformLayout
    1.37
    ConstraintMaker
    1.36
     Efq
    1.33
    Activations Density 1.059%

    No Known Activations