© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7935
    Prev
    Next
    INDEX
    Explanations

    scientific or mathematical expressions

    oai_token-act-pair · gemini-2.0-flash

    Multiplication in scientific contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    aarrggbb
    -0.91
     дописавши
    -0.74
     propOrder
    -0.67
     незавершена
    -0.66
    tagext
    -0.63
     Administrativna
    -0.61
    tagHelperRunner
    -0.60
     kaarangay
    -0.60
    oredCriteria
    -0.59
     виправивши
    -0.59
    POSITIVE LOGITS
     ×
    0.66
    ×
    0.61
    coltà
    0.60
     × 
    0.55
     jadx
    0.54
    adura
    0.54
     Eury
    0.54
    tainen
    0.54
    τύ
    0.54
    ATUS
    0.53
    Activations Density 2.363%

    No Known Activations