© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2291
    Prev
    Next
    INDEX
    Explanations

    language related to financial markets while ignoring proper nouns.

    oai_token-act-pair · gemini-2.0-flash

    stock market

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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>
    -0.79
    Портал
    -0.70
    DebuggerNonUser
    -0.66
    ftagPool
    -0.63
     invokingState
    -0.56
    TestTools
    -0.56
    Datuak
    -0.55
    :✨
    -0.54
    ScopeManager
    -0.52
     distanciation
    -0.51
    POSITIVE LOGITS
    AntiForgeryToken
    0.62
     sensitivity
    0.59
    Cyfeiriadau
    0.55
    reszcie
    0.53
    principalTable
    0.53
    joit
    0.51
     trattato
    0.51
     φυ
    0.50
     useRouter
    0.50
     Haskell
    0.50
    Activations Density 0.456%

    No Known Activations