© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12862
    Prev
    Next
    INDEX
    Explanations

    seemingly, this neuron activates on numbers, possibly in specific contexts (years, measurements) and also some proper nouns (names, places etc.).

    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_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    WebVitals
    -0.67
     مرئيه
    -0.53
    izr
    -0.49
    IsMutable
    -0.47
    <bos>
    -0.47
    GOTREF
    -0.47
     Chwiliwch
    -0.47
    WEBPACK
    -0.47
    XtraEditors
    -0.46
     SSE
    -0.46
    POSITIVE LOGITS
     Meksiku
    0.57
     Waray
    0.54
     odeur
    0.53
    rungsseite
    0.52
     maintien
    0.51
     kasarigan
    0.49
    reactstrap
    0.47
     laman
    0.47
    stretchr
    0.47
     dinh
    0.46
    Activations Density 2.382%

    No Known Activations