© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15503
    Prev
    Next
    INDEX
    Explanations

    double underscore prefixes in variable names, especially when defining main functions

    oai_token-act-pair · gemini-2.0-flash

    __

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    tagHelperRunner
    -1.08
    tvguidetime
    -1.05
     estekak
    -1.04
     transfieras
    -1.04
    SequentialGroup
    -1.04
     CreateTagHelper
    -0.98
    IUrlHelper
    -0.97
     AssemblyProduct
    -0.96
     المعيارى
    -0.94
    setVerticalGroup
    -0.93
    POSITIVE LOGITS
    name
    0.47
    get
    0.46
    on
    0.44
    set
    0.41
     humanas
    0.40
    s
    0.40
    in
    0.40
    com
    0.40
    n
    0.40
    call
    0.39
    Activations Density 1.343%

    No Known Activations