© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14158
    Prev
    Next
    INDEX
    Explanations

    words specifically related to banking and political finance, especially when used in a context of alleged illegality.

    oai_token-act-pair · gemini-2.0-flash

    Bank

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     bank
    -1.01
     bankers
    -0.95
    bank
    -0.90
     banking
    -0.89
     banks
    -0.89
     Bank
    -0.87
     BANK
    -0.86
    Bank
    -0.86
     Banking
    -0.83
     Bankers
    -0.81
    POSITIVE LOGITS
    ğraf
    0.58
    parametrize
    0.55
     preis
    0.53
    rawValue
    0.53
    spoken
    0.51
     prijs
    0.49
     geldig
    0.49
    prm
    0.49
    Externé
    0.49
    riwal
    0.49
    Activations Density 25.971%

    No Known Activations