© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6535
    Prev
    Next
    INDEX
    Explanations

    commas within technical documents

    oai_token-act-pair · gemini-2.0-flash

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    ,
    -0.49
    Indicator
    -0.43
     in
    -0.42
     bagaimana
    -0.42
    urb
    -0.40
    رار
    -0.40
    Locator
    -0.39
     be
    -0.39
     by
    -0.38
     for
    -0.37
    POSITIVE LOGITS
    IntoConstraints
    0.98
    MigrationBuilder
    0.97
     ModelExpression
    0.96
    rungsseite
    0.88
    webElementXpaths
    0.82
    GraphicsUnit
    0.81
    tagHelperRunner
    0.80
    ReusableCell
    0.80
    AddTagHelper
    0.78
    PropertyChanging
    0.77
    Activations Density 2.143%

    No Known Activations