© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11981
    Prev
    Next
    INDEX
    Explanations

    math questions involving finding prime factors or simplifying expressions involving square roots.

    oai_token-act-pair · gemini-2.0-flash

    prime factors of numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    Datuak
    -0.63
     AssemblyTitle
    -0.62
    énario
    -0.60
     boyhood
    -0.59
     Fourth
    -0.59
    forChild
    -0.58
     InputDecoration
    -0.57
    دانشنامهٔ
    -0.57
    esez
    -0.57
     Lordships
    -0.56
    POSITIVE LOGITS
    XmlAccessorType
    0.57
    cshtml
    0.52
    三
    0.50
     Six
    0.47
    $_['
    0.46
     six
    0.45
    的三
    0.45
    ρίς
    0.45
     HasFactory
    0.44
     Tri
    0.44
    Activations Density 2.423%

    No Known Activations