© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10790
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to corporate and personal financial issues and debt

    oai_token-act-pair · gemini-2.0-flash

    financial issues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    ActionButton
    -0.58
     opérateur
    -0.57
    SpringRunner
    -0.57
     {}));
    -0.55
    AccessorTable
    -0.55
     Ostro
    -0.54
    :✨
    -0.53
    moed
    -0.53
    )();
    -0.53
    cinogenicity
    -0.52
    POSITIVE LOGITS
     kasarigan
    0.68
    Case
    0.53
     Case
    0.49
    masse
    0.45
    úcia
    0.45
     noires
    0.44
     Hague
    0.44
    vss
    0.44
     Bankruptcy
    0.44
     Himo
    0.44
    Activations Density 0.778%

    No Known Activations