© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12455
    Prev
    Next
    INDEX
    Explanations

    words or code related to masks for etching semiconductor wafers and to the hardware interfaces used with them.

    oai_token-act-pair · gemini-2.0-flash

    mask

    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
     mask
    -1.07
     Mask
    -1.02
    mask
    -0.96
     masks
    -0.94
     Masks
    -0.90
     MASK
    -0.90
    Mask
    -0.88
     masked
    -0.83
    masks
    -0.79
     masking
    -0.75
    POSITIVE LOGITS
    __(/*!
    0.60
    RegistryLite
    0.54
     famí
    0.52
     doInBackground
    0.49
    ArrowToggle
    0.48
     Homicide
    0.48
     dAtA
    0.47
     udaler
    0.47
    SharedDtor
    0.45
    Trama
    0.44
    Activations Density 14.472%

    No Known Activations