© 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. 11895
    Prev
    Next
    INDEX
    Explanations

    code, specifically, lines/sections of code, that use boolean logic

    oai_token-act-pair · gemini-2.0-flash

    code

    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
     الحره
    -0.67
    లాలు
    -0.60
    醐
    -0.57
    CppCodeGen
    -0.55
    最快更新
    -0.54
     المعيارى
    -0.53
    Brainz
    -0.52
    новниш
    -0.51
    nteral
    -0.50
    americas
    -0.49
    POSITIVE LOGITS
    webElementXpaths
    0.72
    GraphicsUnit
    0.67
    TagMode
    0.64
     >=",
    0.57
     newItem
    0.50
     onData
    0.49
     Boone
    0.47
    onViewCreated
    0.47
     Schedule
    0.47
     Mühl
    0.47
    Activations Density 0.475%

    No Known Activations