© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4612
    Prev
    Next
    INDEX
    Explanations

    mentions of stock exchanges

    oai_token-act-pair · gemini-2.0-flash

    technical terms related to finance

    np_token-act-pair-logits · gpt-4o-mini

    Stock exchanges and companies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     @"/
    -0.63
    InitVars
    -0.55
     createSlice
    -0.54
     TÉCN
    -0.52
     Kommune
    -0.50
    *~*~
    -0.49
    Bibliograf
    -0.48
    ~=
    -0.47
    homonymie
    -0.47
    macs
    -0.46
    POSITIVE LOGITS
    Recognizer
    0.63
    SequentialGroup
    0.60
    parsedMessage
    0.60
    DataAnnotations
    0.57
     дописавши
    0.56
     MainAxisSize
    0.54
    multer
    0.54
    WireFormatLite
    0.54
    pools
    0.52
    venger
    0.52
    Activations Density 0.655%

    No Known Activations