© 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. 11955
    Prev
    Next
    INDEX
    Explanations

    math equations and related surrounding.

    oai_token-act-pair · gemini-2.0-flash

    mathematics/statistics

    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
    InSection
    -0.65
    ftagPool
    -0.57
    makeText
    -0.55
    IntoConstraints
    -0.54
    potranspiration
    -0.50
    newArrayList
    -0.49
     Solon
    -0.49
    hasData
    -0.48
    figer
    -0.48
    bootstrapcdn
    -0.48
    POSITIVE LOGITS
    homonymie
    0.78
     Roskov
    0.63
    EndGlobalSection
    0.58
     Numerade
    0.55
    Bronnen
    0.54
    StoryboardSegue
    0.53
    AlterField
    0.52
     ""],
    0.51
    coefficient
    0.50
    bbler
    0.50
    Activations Density 3.086%

    No Known Activations