© 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. 13212
    Prev
    Next
    INDEX
    Explanations

    code snippets, in particular javascript, including html tags with hyphens, and related keywords

    oai_token-act-pair · gemini-2.0-flash

    (

    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
    IntoConstraints
    -0.64
    estacks
    -0.57
    RegressionTest
    -0.56
     NavController
    -0.53
    fromCharCode
    -0.52
    Zeneca
    -0.52
    onOptions
    -0.49
     SqlCommand
    -0.48
     createState
    -0.48
    BeginContext
    -0.45
    POSITIVE LOGITS
    GroupLayout
    0.60
    LayoutStyle
    0.58
     bedste
    0.55
    
    0.54
    ścio
    0.50
    protoc
    0.50
     Normdatei
    0.50
    whole
    0.49
    intera
    0.49
    ỡng
    0.49
    Activations Density 6.930%

    No Known Activations