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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9100
    Prev
    Next
    INDEX
    Explanations

    vocabulary used when discussing the stock market and financial matters

    oai_token-act-pair · gemini-2.0-flash

    market economics

    np_max-act-logits · gemini-2.0-flash
    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
     mergeFrom
    -0.66
     iprot
    -0.54
    fromnode
    -0.51
    fillType
    -0.47
    Sidenav
    -0.47
    trab
    -0.46
    WritableDatabase
    -0.46
    gone
    -0.45
    RSpec
    -0.45
    forKey
    -0.44
    POSITIVE LOGITS
     bulls
    0.64
     cortas
    0.63
     créativité
    0.59
     rompecabezas
    0.59
     bull
    0.58
     bears
    0.57
     eccell
    0.57
     dirigez
    0.56
     tartalomajánló
    0.56
    bull
    0.56
    Activations Density 2.855%

    No Known Activations