© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 5768
    Prev
    Next
    INDEX
    Explanations

    financial news articles

    oai_token-act-pair · gemini-2.0-flash

    Economy

    np_max-act-logits · gemini-2.0-flash

    the

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    Aiheesta
    -0.51
    原始内容存档于
    -0.50
    ngilizce
    -0.47
     Ore
    -0.47
    urt
    -0.47
    agd
    -0.46
     שוליים
    -0.45
    Kaynakça
    -0.45
    HasOne
    -0.45
    <?=$
    -0.44
    POSITIVE LOGITS
    ViewFeatures
    0.74
     createState
    0.68
    RegressionTest
    0.61
     EconPapers
    0.60
    ="@+
    0.60
    kháu
    0.57
    Parcelize
    0.56
     CreateTagHelper
    0.56
    :✨
    0.55
    ArgumentParser
    0.55
    Activations Density 2.562%

    No Known Activations