© 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. 12890
    Prev
    Next
    INDEX
    Explanations

    code comments indicating license and copyright information

    oai_token-act-pair · gemini-2.0-flash

    c

    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
    ValueStyle
    -0.67
     autorytatywna
    -0.62
    })*/
    -0.62
    Cyfeiriadau
    -0.61
     يتيمه
    -0.61
     propTypes
    -0.59
    Autoritní
    -0.59
    WebServlet
    -0.54
    PendingIntent
    -0.54
    setupUi
    -0.54
    POSITIVE LOGITS
    发表于
    0.59
    ácido
    0.41
     Arhivirano
    0.40
     PropertyChanged
    0.39
    tences
    0.38
     Glamour
    0.38
    atars
    0.38
     McRae
    0.37
    исленность
    0.36
     clays
    0.36
    Activations Density 1.501%

    No Known Activations