© 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. 14006
    Prev
    Next
    INDEX
    Explanations

    words related to source code and related artifacts, and also finds occurrences of the word "hand" (often in the context of hand-written code)

    oai_token-act-pair · gemini-2.0-flash

    coding

    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
    ViewFeatures
    -0.86
    Personensuche
    -0.65
    XmlType
    -0.65
     nahilalakip
    -0.62
     EconPapers
    -0.62
    adaptiveStyles
    -0.61
    sidemargin
    -0.59
    SpringBootTest
    -0.57
    Simult
    -0.54
     lenker
    -0.54
    POSITIVE LOGITS
     homemade
    0.73
    DIY
    0.70
    custom
    0.68
     DIY
    0.67
    Custom
    0.67
    Homemade
    0.66
     handmade
    0.65
     custom
    0.63
     Customized
    0.62
    自制
    0.60
    Activations Density 0.755%

    No Known Activations