© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12717
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially related to variable declarations, assignments, loops, and boolean logic

    oai_token-act-pair · gemini-2.0-flash

    Zero and false

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     <<<<<<<<<<<<<<
    -0.92
    DrawerToggle
    -0.77
    BeginInit
    -0.75
    HomeAsUpEnabled
    -0.75
     الحره
    -0.73
    enumi
    -0.71
    ()])
    -0.71
     المعيارى
    -0.71
    ">—
    -0.70
    }]{
    -0.69
    POSITIVE LOGITS
    SuppressLint
    0.47
    RunWith
    0.44
    cookieParser
    0.43
    紧
    0.43
     chip
    0.42
    inner
    0.41
    Cursors
    0.41
    pen
    0.41
    Chip
    0.40
     pen
    0.40
    Activations Density 0.660%

    No Known Activations