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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 3-GEMMASCOPE-TRANSCODER-16K
    4. 10340
    Prev
    Next
    INDEX
    Explanations

    references to scientific funding, especially from China, and citations including the last name "Newey".

    oai_token-act-pair · gemini-2.0-flash

    Funding grants

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     урна
    -0.48
     Forster
    -0.48
    maphore
    -0.47
     lebaran
    -0.46
    стве
    -0.44
    ulum
    -0.44
     跳转至
    -0.41
    TypeString
    -0.40
    lès
    -0.39
     ben
    -0.39
    POSITIVE LOGITS
    الإنجليزية
    0.82
     Meksiku
    0.81
     estimés
    0.77
    DockStyle
    0.75
     Савезне
    0.71
    ArgsConstructor
    0.70
    LookAnd
    0.68
    bootstrapcdn
    0.66
    adpleegd
    0.65
     mohair
    0.65
    Activations Density 1.118%

    No Known Activations