© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4512
    Prev
    Next
    INDEX
    Explanations

    mentions of first names, last names, and phone numbers

    oai_token-act-pair · gemini-2.0-flash

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    Predecesor
    -0.52
    فس
    -0.46
    imize
    -0.43
    Anak
    -0.43
    WriteTagHelper
    -0.42
    ORAGE
    -0.42
     Roskov
    -0.42
     Mehta
    -0.42
    createQuery
    -0.42
     "..\..\
    -0.42
    POSITIVE LOGITS
     surnames
    0.94
     surname
    0.90
     Parcelable
    0.78
     Surname
    0.77
     initComponents
    0.77
    %";
    0.75
    Hentet
    0.75
     unknownFields
    0.72
    Становништво
    0.72
    %")
    0.71
    Activations Density 0.713%

    No Known Activations