© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10730
    Prev
    Next
    INDEX
    Explanations

    numbers, percentages, and units of measurement

    oai_token-act-pair · gemini-2.0-flash

    numerical data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    oredCriteria
    -0.77
     виправивши
    -0.76
    AddTagHelper
    -0.69
    دانشنامهٔ
    -0.69
    invokeLater
    -0.66
    featureID
    -0.63
    قایناق‌لار
    -0.63
    GEBURTSDATUM
    -0.63
    енча
    -0.61
    writeField
    -0.60
    POSITIVE LOGITS
    EndContext
    0.52
     frigo
    0.51
    Btu
    0.49
     Jaffe
    0.48
     gigante
    0.47
    umán
    0.46
     Society
    0.45
    peti
    0.45
    شتی
    0.45
     há
    0.44
    Activations Density 1.743%

    No Known Activations