© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2159
    Prev
    Next
    INDEX
    Explanations

    words related to financial trading and personal pronouns

    oai_token-act-pair · gemini-2.0-flash

    financial market trading

    np_max-act-logits · gemini-2.0-flash
    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
    ⓧ
    -0.68
     nakalista
    -0.66
     market
    -0.62
    AddTagHelper
    -0.61
    market
    -0.61
    MARKET
    -0.60
     Market
    -0.60
    InjectAttribute
    -0.60
    ImageIcon
    -0.58
    Market
    -0.53
    POSITIVE LOGITS
    ąpi
    0.54
    reportWebVitals
    0.52
    astă
    0.50
     <<<<<<<<<<<<<<
    0.47
    Personendaten
    0.46
     trade
    0.46
    localctx
    0.46
    FQ
    0.45
    lq
    0.44
     Accesat
    0.43
    Activations Density 5.190%

    No Known Activations