© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7470
    Prev
    Next
    INDEX
    Explanations

    a mix of programming-related commands and legal terminology

    oai_token-act-pair · gemini-2.0-flash

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     JADX
    -0.73
     lenker
    -0.68
    setVerticalGroup
    -0.62
    تقاوى
    -0.60
    DataAnnotations
    -0.59
    richTextPanel
    -0.59
    sizeCache
    -0.57
    LDAP
    -0.57
     Jop
    -0.56
    reactstrap
    -0.55
    POSITIVE LOGITS
    ()}}
    0.65
    )$/,
    0.60
    gerufen
    0.57
    poons
    0.55
    <bos>
    0.52
     kasarigan
    0.51
    ]+=
    0.50
    )]=
    0.49
     couche
    0.48
    ))=
    0.48
    Activations Density 1.202%

    No Known Activations