© 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. 3394
    Prev
    Next
    INDEX
    Explanations

    corporate PR announcements

    oai_token-act-pair · gemini-2.0-flash

    banks

    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
     Roskov
    -0.62
    AddHtmlAttribute
    -0.60
    rungsseite
    -0.59
     Мексичка
    -0.58
    Fprintf
    -0.54
    ỳ
    -0.53
    KommentareTeilen
    -0.52
    WidgetItem
    -0.52
    moveToFirst
    -0.51
    Protocols
    -0.51
    POSITIVE LOGITS
     Bank
    0.90
    Bank
    0.86
    BANK
    0.84
     bank
    0.78
    bank
    0.77
     BANK
    0.75
     insurance
    0.71
     banks
    0.71
     Allianz
    0.66
     HSBC
    0.64
    Activations Density 0.931%

    No Known Activations