© 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. 15814
    Prev
    Next
    INDEX
    Explanations

    the word "quantitative"

    oai_token-act-pair · gemini-2.0-flash

    quantitative

    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
     [''],
    -0.63
    er
    -0.63
    <bos>
    -0.60
     <<-
    -0.58
    FormsModule
    -0.58
    ER
    -0.57
     iscri
    -0.57
     UserDao
    -0.55
    erd
    -0.54
     estimés
    -0.53
    POSITIVE LOGITS
    rrggbb
    0.80
    aarrggbb
    0.78
     محفوظة
    0.77
    sprozess
    0.72
    tocin
    0.71
    riwal
    0.71
     Cytometry
    0.70
    InjectAttribute
    0.69
     onAnimation
    0.69
    getSeconds
    0.67
    Activations Density 1.733%

    No Known Activations