© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12369
    Prev
    Next
    INDEX
    Explanations

    elements of math problems involving prime factors and composite numbers

    oai_token-act-pair · gemini-2.0-flash

    prime

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    __(/*!
    -0.59
     AspNetCore
    -0.59
    ándolos
    -0.52
    gcd
    -0.52
    CompilerServices
    -0.52
     DialogInterface
    -0.52
    dihydro
    -0.51
    CodeDom
    -0.51
    Geplaatst
    -0.49
    enschappe
    -0.48
    POSITIVE LOGITS
     فريبيس
    0.65
     للاسماء
    0.62
     paradas
    0.56
     Lexikon
    0.51
     φορ
    0.50
    >//
    0.48
     mxArray
    0.46
     विश्वसनीयता
    0.46
    iprot
    0.46
    ustice
    0.45
    Activations Density 1.888%

    No Known Activations