© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10939
    Prev
    Next
    INDEX
    Explanations

    a wide variety of words related to technology, science, history, and common negative words.

    oai_token-act-pair · gemini-2.0-flash

    coding/technical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    <bos>
    -1.13
    Бахар
    -0.52
     referrerpolicy
    -0.51
    География
    -0.49
     addSubview
    -0.49
     AssemblyTitle
    -0.47
     StatefulWidget
    -0.47
     descal
    -0.46
    ագրություններ
    -0.46
     autorytatywna
    -0.46
    POSITIVE LOGITS
    oredCriteria
    0.72
    bewerken
    0.60
     مشين
    0.57
    parsedMessage
    0.56
    qrstuvwxyz
    0.54
    unmodifiable
    0.54
    iburg
    0.52
    sizeCache
    0.52
     đâu
    0.51
    Duel
    0.51
    Activations Density 7.075%

    No Known Activations