© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 698
    Prev
    Next
    INDEX
    Explanations

    mentions of mathematical terms, data analysis, and experiments.

    oai_token-act-pair · gemini-2.0-flash

    count

    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
    didSet
    -0.79
    uesday
    -0.65
    nologies
    -0.62
    MemoryWarning
    -0.59
     lastName
    -0.59
     démocr
    -0.59
     fallu
    -0.59
     eventdata
    -0.58
     setType
    -0.58
    loroethane
    -0.58
    POSITIVE LOGITS
     counting
    0.81
     counted
    0.75
    Counting
    0.69
     Counting
    0.69
    RenderAtEndOf
    0.65
     COUNT
    0.65
     calculation
    0.61
     counts
    0.61
    算
    0.59
     Counts
    0.59
    Activations Density 1.154%

    No Known Activations