© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4281
    Prev
    Next
    INDEX
    Explanations

    large numbers, especially those pertaining to statistics and government

    oai_token-act-pair · gemini-2.0-flash

    large quantities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     hundreds
    -0.79
     ratusan
    -0.76
     eighty
    -0.74
    hundreds
    -0.71
     thousands
    -0.68
    thousands
    -0.67
     sixty
    -0.67
     yaklaşık
    -0.66
     seventy
    -0.66
     forty
    -0.63
    POSITIVE LOGITS
    memoized
    0.73
     <",
    0.71
    RTLD
    0.71
    qrstuvwxyz
    0.68
    [])
    0.67
    fromnode
    0.66
    DoubleQuotes
    0.65
    protoimpl
    0.65
    PyExc
    0.65
    Tembelea
    0.62
    Activations Density 1.198%

    No Known Activations