© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14596
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "PAT" and the word "patent".

    oai_token-act-pair · gemini-2.0-flash

    terms related to patents and legal concepts

    np_token-act-pair-logits · gpt-4o-mini

    Pat

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     Ram
    -0.44
    럴
    -0.42
     pol
    -0.41
    BLO
    -0.41
     autor
    -0.41
    ke
    -0.40
    ifie
    -0.40
    eran
    -0.40
    ofen
    -0.40
    pli
    -0.39
    POSITIVE LOGITS
    ValueStyle
    1.17
     AssemblyCulture
    0.92
    ReusableCell
    0.89
    extAlignment
    0.87
    SequentialGroup
    0.82
     dAtA
    0.78
    MigrationBuilder
    0.78
    AddHtmlAttribute
    0.77
    BufferException
    0.76
    WebVitals
    0.76
    Activations Density 0.406%

    No Known Activations