© 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. 12198
    Prev
    Next
    INDEX
    Explanations

    boolean expressions, loops, and other common programming constructs

    oai_token-act-pair · gemini-2.0-flash

    control flow statements

    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
    nor
    -0.52
    setHorizontal
    -0.50
     aidant
    -0.49
     assoluto
    -0.48
    AssignableFrom
    -0.47
    ]-->
    -0.47
    ಾದ
    -0.47
     corpi
    -0.47
     origini
    -0.46
    bar
    -0.46
    POSITIVE LOGITS
    oredCriteria
    0.62
    djangoproject
    0.58
    fillType
    0.57
    ValueStyle
    0.57
    scrapy
    0.56
    IUrlHelper
    0.56
    InjectAttribute
    0.56
    PreExecute
    0.54
     protoimpl
    0.53
     незавершена
    0.53
    Activations Density 3.719%

    No Known Activations