Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 13519
    Prev
    Next
    INDEX
    Explanations

    code syntax defining enumerated types, cases, and initializers

    oai_token-act-pair · gemini-2.0-flash

    case

    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
    MessageOf
    -0.60
     Yew
    -0.60
    Viitteet
    -0.59
    NameInMap
    -0.59
    IntoConstraints
    -0.58
    ?
    
    -0.57
     Poy
    -0.57
     Cok
    -0.56
     ETA
    -0.56
    hound
    -0.56
    POSITIVE LOGITS
    <bos>
    1.18
    ’
    0.46
     building
    0.45
    basicConfig
    0.44
    HasForeignKey
    0.44
    '
    0.43
     sac
    0.43
     to
    0.41
    JAKARTA
    0.41
     للمعارف
    0.40
    Activations Density 3.013%

    No Known Activations