© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15918
    Prev
    Next
    INDEX
    Explanations

    mentions of numbers, money, percentages, amounts, and countries with the context of European economics

    oai_token-act-pair · gemini-2.0-flash

    common stopwords Method used: 1 — Reason: MAX_ACTIVATING_TOKENS are predominantly articles/prepositions (the, in, of, is, at, other) — common stopwords

    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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     euro
    -1.20
     European
    -1.14
     Euro
    -1.13
    euro
    -1.13
     Europe
    -1.10
     euros
    -1.07
    European
    -1.07
     €
    -1.06
     EUROPEAN
    -1.04
    Europe
    -0.99
    POSITIVE LOGITS
     Efq
    0.95
     itſelf
    0.93
     myſelf
    0.84
     ſeveral
    0.81
     Jefus
    0.80
     CreateTagHelper
    0.79
     Majefty
    0.78
     pleaſure
    0.76
     Theſe
    0.75
     Monfieur
    0.75
    Activations Density 2.110%

    No Known Activations