© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5539
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the financial industry, especially investments and company mergers

    oai_token-act-pair · gemini-2.0-flash

    finance and company names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    脚注の使い方
    -0.60
     zove
    -0.56
    MessageTagHelper
    -0.53
    InputTagHelper
    -0.53
    Lähteet
    -0.52
     contactez
    -0.50
     alá
    -0.50
    owę
    -0.49
     buch
    -0.49
     Nauk
    -0.49
    POSITIVE LOGITS
     فريبيس
    0.76
     common
    0.57
     Common
    0.50
    Common
    0.49
    MethodManager
    0.49
    common
    0.49
     communs
    0.48
    Datuak
    0.47
    execSQL
    0.47
    يميديا
    0.47
    Activations Density 3.525%

    No Known Activations