© 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. 15802
    Prev
    Next
    INDEX
    Explanations

    mathematical and chemical formulas along with related terminology

    oai_token-act-pair · gemini-2.0-flash

    say "math terms"

    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
     Numbers
    -0.93
     NUMBERS
    -0.91
    numbers
    -0.89
     numbers
    -0.88
     quantities
    -0.84
     Quantities
    -0.83
    Numbers
    -0.81
    IsContent
    -0.80
    Amounts
    -0.78
    Autoritní
    -0.77
    POSITIVE LOGITS
     number
    0.45
    po
    0.41
    ays
    0.40
    gridx
    0.38
     po
    0.38
    Techniques
    0.38
     amount
    0.36
     multiple
    0.35
    minecraft
    0.34
    бина
    0.34
    Activations Density 10.010%

    No Known Activations