© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2533
    Prev
    Next
    INDEX
    Explanations

    mathematical notation involving trigonometric functions, exponents, and Greek letters

    oai_token-act-pair · gemini-2.0-flash

    specific mathematical functions or expressions

    np_token-act-pair-logits · gpt-4o-mini

    math formulas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     g
    -0.51
     aapt
    -0.44
    üsü
    -0.41
    HasIndex
    -0.41
    writeField
    -0.40
    featureID
    -0.39
     By
    -0.37
    LOSS
    -0.37
     D
    -0.37
    らく
    -0.36
    POSITIVE LOGITS
    tvguidetime
    0.82
    WebControls
    0.72
     يتيمه
    0.71
    ANDUM
    0.71
    SourceChecksum
    0.67
     disambiguazione
    0.66
    ContentAsync
    0.66
    virons
    0.66
     Roskov
    0.64
    ⏎
    0.64
    Activations Density 0.920%

    No Known Activations