© 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. 9676
    Prev
    Next
    INDEX
    Explanations

    medical and scientific language, especially prefixes and suffixes, chemical compounds, and units of measurement

    oai_token-act-pair · gemini-2.0-flash

    Random text snippets

    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
    n
    -0.91
    m
    -0.91
    k
    -0.90
    d
    -0.82
    t
    -0.76
    g
    -0.75
    l
    -0.74
    z
    -0.71
    re
    -0.68
    p
    -0.65
    POSITIVE LOGITS
    er
    0.82
    en
    0.78
    a
    0.75
    o
    0.74
     nakalista
    0.73
    an
    0.72
    es
    0.71
    ed
    0.68
    ا
    0.66
    oa
    0.65
    Activations Density 6.714%

    No Known Activations