© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1884
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and expressions, including variable names

    oai_token-act-pair · gemini-2.0-flash

    Math equations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    AutoField
    -0.94
    BeginInit
    -0.66
     initComponents
    -0.62
    XmlAccessorType
    -0.61
    herin
    -0.60
    Koordinaten
    -0.58
     InputDecoration
    -0.57
    sidemargin
    -0.56
    脚注の使い方
    -0.56
    NamedQuery
    -0.56
    POSITIVE LOGITS
    SqlSession
    0.51
     key
    0.47
     sent
    0.46
    Initializable
    0.45
    ibrill
    0.44
    sprogramm
    0.43
    monės
    0.43
    sent
    0.42
     under
    0.42
    alnız
    0.42
    Activations Density 3.101%

    No Known Activations