© 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. 3497
    Prev
    Next
    INDEX
    Explanations

    lines of code, potentially of different languages

    oai_token-act-pair · gemini-2.0-flash

    math and code

    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
    Xna
    -0.56
    UnusedPrivate
    -0.51
    Argument
    -0.50
    saraba
    -0.50
    delwed
    -0.49
     Argument
    -0.48
    thren
    -0.47
    unzel
    -0.47
     vị
    -0.47
     아니라
    -0.47
    POSITIVE LOGITS
    Personensuche
    0.60
    ंदीखरीदारी
    0.58
    InstanceState
    0.55
    dataclass
    0.54
     contextLoads
    0.52
    onViewCreated
    0.51
    الدراسه
    0.50
    Separate
    0.49
     للمعارف
    0.49
     mauvaises
    0.48
    Activations Density 0.083%

    No Known Activations