© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5817
    Prev
    Next
    INDEX
    Explanations

    parts of code that can return or exit under certain conditions

    oai_token-act-pair · gemini-2.0-flash

    Semicolons and parentheses

    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
    AndEndTag
    -0.87
     EconPapers
    -0.76
     springfox
    -0.71
    TemporalType
    -0.67
     useSelector
    -0.66
     noqa
    -0.65
    inerja
    -0.64
    Pautan
    -0.62
     dAtA
    -0.62
     boomer
    -0.61
    POSITIVE LOGITS
     keeping
    0.50
    ніципа
    0.45
     keep
    0.44
    keeping
    0.44
     Keeping
    0.43
    kez
    0.43
     Staying
    0.43
     ماش
    0.42
     Keep
    0.42
     Here
    0.41
    Activations Density 0.231%

    No Known Activations