© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7254
    Prev
    Next
    INDEX
    Explanations

    financial data, including loans, banks, and money.

    oai_token-act-pair · gemini-2.0-flash

    terms related to finance or banking

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

    Finance and foreign words

    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
     ModelExpression
    -0.61
     ISNI
    -0.57
    parsedMessage
    -0.56
     AttributeSet
    -0.56
    ãy
    -0.55
     appointing
    -0.54
    Controllo
    -0.50
     Camin
    -0.50
     gins
    -0.50
    setVerticalGroup
    -0.50
    POSITIVE LOGITS
    ChildScrollView
    0.61
     personal
    0.61
     car
    0.56
    unst
    0.56
     NgModule
    0.56
     الشخص
    0.54
    olari
    0.54
     CAR
    0.54
     Un
    0.54
     maïs
    0.53
    Activations Density 0.899%

    No Known Activations