© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11269
    Prev
    Next
    INDEX
    Explanations

    words related to banking, finance, and money management

    oai_token-act-pair · gemini-2.0-flash

    balance

    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
    onViewCreated
    -0.56
    rehension
    -0.53
     financiers
    -0.52
    providedIn
    -0.50
     financially
    -0.50
    出版年
    -0.48
     financial
    -0.48
     financiero
    -0.48
    Finanz
    -0.48
     Financial
    -0.47
    POSITIVE LOGITS
     balance
    2.19
     Balance
    1.98
     balances
    1.90
    balance
    1.89
    Balance
    1.84
     BALANCE
    1.69
    BALANCE
    1.58
    balances
    1.48
     balanced
    1.45
     balans
    1.41
    Activations Density 5.265%

    No Known Activations