© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6585
    Prev
    Next
    INDEX
    Explanations

    East Asian names

    oai_token-act-pair · gemini-2.0-flash

    Chinese names or initials

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -1.28
    Бахар
    -0.97
     ComVisible
    -0.94
     itſelf
    -0.90
     Мексичка
    -0.82
    AndroidJUnit
    -0.81
    Demografie
    -0.80
    цездатний
    -0.80
     estimés
    -0.79
     Савезне
    -0.77
    POSITIVE LOGITS
     .
    0.66
    .
    0.50
    0.47
    ↵
    0.47
    ↵↵
    0.46
    <strong>
    0.46
     But
    0.43
     brand
    0.43
    [
    0.43
    ForType
    0.43
    Activations Density 0.144%
    No Known Activations