© 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. 10439
    Prev
    Next
    INDEX
    Explanations

    the word "agenda" and sometimes the word "Institute"

    oai_token-act-pair · gemini-2.0-flash

    meetings, research, goals

    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
    expandindo
    -0.99
    }")
    -0.95
    <bos>
    -0.90
    makeConstraints
    -0.90
    DockStyle
    -0.82
    >",
    -0.82
    )");
    -0.81
     >=",
    -0.81
    脚注の使い方
    -0.80
    setVerticalGroup
    -0.79
    POSITIVE LOGITS
     betrekking
    0.77
    anskje
    0.74
    достатки
    0.65
     diikuti
    0.64
     or
    0.63
     图案
    0.62
     precisione
    0.61
     but
    0.60
     along
    0.59
     Above
    0.57
    Activations Density 1.084%

    No Known Activations