© 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. 14343
    Prev
    Next
    INDEX
    Explanations

    mathematical notation in research publications

    oai_token-act-pair · gemini-2.0-flash

    code/math symbols

    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
    tagHelperRunner
    -0.89
     betweenstory
    -0.81
     مشين
    -0.79
     Италијани
    -0.72
     للمعارف
    -0.71
     autorytatywna
    -0.70
    
    -0.68
    rungsseite
    -0.67
    verwijspagina
    -0.65
    ThroughAttribute
    -0.65
    POSITIVE LOGITS
    CIC
    0.51
    ICI
    0.50
    propyl
    0.50
    horm
    0.50
    CIT
    0.49
     springfox
    0.48
    mento
    0.47
    NAL
    0.47
    ENTI
    0.46
    form
    0.46
    Activations Density 6.847%

    No Known Activations