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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14076
    Prev
    Next
    INDEX
    Explanations

    program code and initialization procedures

    oai_token-act-pair · gemini-2.0-flash

    init

    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
    init
    -1.98
     init
    -1.93
     Init
    -1.66
    Init
    -1.66
    INIT
    -1.51
     initialization
    -1.37
     INIT
    -1.36
    初始化
    -1.34
     initialized
    -1.29
     initi
    -1.28
    POSITIVE LOGITS
    aarrggbb
    0.60
    }{*}{
    0.59
    EndGlobalSection
    0.56
    ViewFeatures
    0.52
    Datuak
    0.52
     thất
    0.52
    AutoScaleMode
    0.51
    JspWriter
    0.50
     planètes
    0.48
    setOnAction
    0.47
    Activations Density 12.858%

    No Known Activations