© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8421
    Prev
    Next
    INDEX
    Explanations

    text is discussing money and bank accounts

    oai_token-act-pair · gemini-2.0-flash

    bank

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Мексичка
    -0.50
    pexpr
    -0.49
    uxxxx
    -0.47
    ử
    -0.45
     Pulitzer
    -0.45
    évaluateur
    -0.45
    Pill
    -0.45
    xtick
    -0.44
     Francis
    -0.44
     lungs
    -0.44
    POSITIVE LOGITS
     bank
    1.78
    bank
    1.54
     Bank
    1.48
    Bank
    1.43
     BANK
    1.41
    BANK
    1.34
     banks
    1.33
     banking
    1.30
     account
    1.22
    banks
    1.18
    Activations Density 1.156%

    No Known Activations