© 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. 11154
    Prev
    Next
    INDEX
    Explanations

    parts of PHP code relating to SQL queries

    oai_token-act-pair · gemini-2.0-flash

    ['

    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
    parsedMessage
    -0.72
     canst
    -0.69
     PLW
    -0.67
     démocr
    -0.66
     efficaces
    -0.63
    ípios
    -0.63
    存于互联网档案馆
    -0.63
     originaux
    -0.63
     trò
    -0.61
    endió
    -0.61
    POSITIVE LOGITS
    <bos>
    1.53
    хьтан
    0.62
    ArrowToggle
    0.54
    AddTagHelper
    0.50
     T
    0.48
    '
    0.47
     and
    0.47
    <?
    0.46
    T
    0.45
    RegistryLite
    0.43
    Activations Density 2.500%

    No Known Activations