© 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. 11721
    Prev
    Next
    INDEX
    Explanations

    variable assignments in code or poorly formatted text

    oai_token-act-pair · gemini-2.0-flash

    code, formulas

    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
     estekak
    -1.02
     esternos
    -1.00
     '\\;'
    -0.89
     Италијани
    -0.86
     مشين
    -0.86
    sizeCache
    -0.83
    reportWebVitals
    -0.83
     nahilalakip
    -0.81
    UnusedPrivate
    -0.79
    EDEFAULT
    -0.79
    POSITIVE LOGITS
    kloped
    0.45
    RectangleBorder
    0.42
    Computer
    0.41
     Maxi
    0.41
     piscina
    0.39
    fits
    0.39
    влений
    0.38
    žně
    0.38
    วรร
    0.38
    (/[
    0.38
    Activations Density 3.463%

    No Known Activations