© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4509
    Prev
    Next
    INDEX
    Explanations

    the phrase "prior art" which is used in legal and technical writing

    oai_token-act-pair · gemini-2.0-flash

    prior

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    enumii
    -0.77
    الإنجليزية
    -0.76
    </b>
    -0.75
     dreamstime
    -0.72
     belangrij
    -0.71
    reportWebVitals
    -0.71
    ########.
    -0.71
     pngtree
    -0.71
     Tatsache
    -0.71
    #+#
    -0.71
    POSITIVE LOGITS
    visiae
    0.59
    endphp
    0.55
    TacToe
    0.54
     réjou
    0.52
    posób
    0.51
     "','
    0.50
     hâte
    0.49
    __":
    0.49
    uset
    0.48
    '`
    0.47
    Activations Density 2.093%

    No Known Activations