© 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. 4590
    Prev
    Next
    INDEX
    Explanations

    this neuron finds portions of documents with unique formatting styles, like sections with unusual spacing or use of delimiters.

    oai_token-act-pair · gemini-2.0-flash

    Technical/mathematical text

    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
    <strong>
    -1.45
    frac
    -1.07
    #%%
    -0.70
    ];//
    -0.57
    ");//
    -0.55
    ",@"
    -0.55
    //
    -0.55
    {}".
    -0.54
     [%
    -0.54
    outState
    -0.53
    POSITIVE LOGITS
    <em>
    0.82
     متعلقه
    0.79
    bootstrapcdn
    0.73
    Datuak
    0.70
    /*
    0.69
    rungsseite
    0.63
    homonymie
    0.61
    ⓧ
    0.60
     ligiloj
    0.59
    setVerticalGroup
    0.58
    Activations Density 0.862%

    No Known Activations