© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4906
    Prev
    Next
    INDEX
    Explanations

    instances of the word "byte" in programming contexts

    oai_token-act-pair · gemini-2.0-flash

    byte

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    bin
    -0.84
    t
    -0.82
    ting
    -0.81
    s
    -0.79
    tes
    -0.79
    lin
    -0.78
    ts
    -0.77
    了
    -0.77
    tas
    -0.75
    ton
    -0.73
    POSITIVE LOGITS
     CreateTagHelper
    1.23
    XmlAccessorType
    1.22
    SBATCH
    1.19
    berdayakan
    1.13
    TagMode
    1.11
    tagHelperRunner
    1.10
     newBuilder
    1.05
     createSlice
    1.03
     zijne
    1.02
    xase
    1.02
    Activations Density 1.077%

    No Known Activations