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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 7-GEMMASCOPE-TRANSCODER-16K
    4. 7145
    Prev
    Next
    INDEX
    Explanations

    words related to fundraising events for charitable causes

    oai_token-act-pair · gemini-2.0-flash

    society

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    AddTagHelper
    -1.06
    IVEREF
    -0.84
    NewUrlParser
    -0.71
     препратки
    -0.65
    AddHtmlAttribute
    -0.65
    ParallelGroup
    -0.64
    InjectAttribute
    -0.64
     lenker
    -0.62
    PerformLayout
    -0.61
    PointerException
    -0.60
    POSITIVE LOGITS
     fundraising
    0.49
    latego
    0.49
    fund
    0.48
     recaud
    0.46
    eigen
    0.45
     domestiques
    0.42
    MockBean
    0.41
     raised
    0.39
     egen
    0.39
    Fundraising
    0.38
    Activations Density 0.271%

    No Known Activations