© 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. 12322
    Prev
    Next
    INDEX
    Explanations

    the word "exception," sometimes in conjunction with words like "agree" or "public"

    oai_token-act-pair · gemini-2.0-flash

    exception

    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
    ^(@)
    -1.66
    )");
    -1.62
    %");
    -1.52
     $_"
    -1.51
    .)}
    -1.49
    BibitemShut
    -1.49
    >\<^
    -1.48
    )++;
    -1.47
    "]);
    -1.46
    !")
    -1.46
    POSITIVE LOGITS
    .
    1.11
     
    1.02
    a
    1.00
    ,
    0.99
    <em>
    0.99
     (
    0.93
     in
    0.92
    -
    0.88
    ↵
    0.88
     on
    0.88
    Activations Density 2.198%

    No Known Activations