© 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. 12635
    Prev
    Next
    INDEX
    Explanations

    the words "lean" and "projection"

    oai_token-act-pair · gemini-2.0-flash

    lean

    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
    weile
    -0.81
    المناصب
    -0.75
    aarrggbb
    -0.71
     "}";
    -0.64
    $")
    -0.64
     '\\;'
    -0.61
     lượt
    -0.61
     zeitung
    -0.61
    paksa
    -0.60
    Tazama
    -0.60
    POSITIVE LOGITS
    MathML
    0.82
    tvguidetime
    0.75
    脚注の使い方
    0.71
    <bos>
    0.71
    Personendaten
    0.69
    printStackTrace
    0.68
    意思
    0.64
    はじめに
    0.63
    amarin
    0.63
    AnchorStyles
    0.62
    Activations Density 0.898%

    No Known Activations