© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3520
    Prev
    Next
    INDEX
    Explanations

    words associated with software deployment and integration, especially related to Jenkins, Gitlab, and PHP.

    oai_token-act-pair · gemini-2.0-flash

    CI/CD pipelines, software development

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    enumii
    -0.54
     fine
    -0.51
    BrowserModule
    -0.49
    fecture
    -0.45
     invokingState
    -0.44
     administrar
    -0.44
    lē
    -0.42
    scanf
    -0.41
     prestar
    -0.41
     cura
    -0.41
    POSITIVE LOGITS
     فريبيس
    0.87
    SBATCH
    0.73
     actionMode
    0.66
     brooms
    0.63
    expandindo
    0.61
    RenderAtEndOf
    0.61
    Билгалдахарш
    0.59
    WithIOException
    0.59
     Ouv
    0.59
    complexContent
    0.59
    Activations Density 2.091%

    No Known Activations