© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12741
    Prev
    Next
    INDEX
    Explanations

    lines of code that import Java or com libraries

    oai_token-act-pair · gemini-2.0-flash

    code imports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    НИК
    -0.59
    ↹
    -0.59
    الحياه
    -0.57
    CPtr
    -0.55
     iprot
    -0.54
    adalu
    -0.54
    туга
    -0.54
     elif
    -0.54
     ErrIntOverflow
    -0.54
    transQ
    -0.53
    POSITIVE LOGITS
    ISupport
    0.56
    fxml
    0.43
     intptr
    0.42
    PRNewswire
    0.41
     chemise
    0.40
    DoubleQuotes
    0.39
    onAttach
    0.39
     Laplacian
    0.37
    Datuak
    0.36
    Kontrola
    0.36
    Activations Density 0.429%

    No Known Activations