© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7701
    Prev
    Next
    INDEX
    Explanations

    words describing actions or activity in a variety of contexts, including legal, religious, technical and social situations (This is a bit of a catch-all neuron; it's hard to be more specific)

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     Wikimedijinoj
    -1.11
     kasarigan
    -1.09
    UnusedPrivate
    -1.02
    :✨
    -0.98
     resourceCulture
    -0.93
    évaluateur
    -0.89
     مشين
    -0.88
    MENAFN
    -0.88
    Datuak
    -0.87
    íncia
    -0.85
    POSITIVE LOGITS
     gì
    0.41
    '
    0.40
    <bos>
    0.39
    fseek
    0.36
     Per
    0.35
     "
    0.35
     setEmail
    0.34
    ビール
    0.33
    這樣
    0.33
    ้อมูล
    0.33
    Activations Density 12.675%

    No Known Activations