© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5540
    Prev
    Next
    INDEX
    Explanations

    code-related terms like dependencies, implementation, and artifacts

    oai_token-act-pair · gemini-2.0-flash

    specific programming keywords and libraries

    np_token-act-pair-logits · gpt-4o-mini

    code/XML

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    rzost
    -0.56
    findOneAndUpdate
    -0.53
     stanovnika
    -0.48
    structing
    -0.47
    andoah
    -0.46
     trail
    -0.45
     Recherche
    -0.44
     Trail
    -0.44
     Arduino
    -0.43
    >())
    -0.43
    POSITIVE LOGITS
     betweenstory
    0.66
    UnsafeEnabled
    0.66
    الحياه
    0.56
     متعلقه
    0.55
     Autorizaciones
    0.54
    AnimationsModule
    0.53
     makeStyles
    0.51
    ěry
    0.51
    BagLayout
    0.50
     gynhyrchwyd
    0.50
    Activations Density 3.021%

    No Known Activations