© 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. 14890
    Prev
    Next
    INDEX
    Explanations

    Latex or other math notation.

    oai_token-act-pair · gemini-2.0-flash

    technical jargon or notation

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

    math equations and symbols

    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
     "..\..\..\
    -0.66
     "..\..\
    -0.64
     unknownFields
    -0.61
    WireFormatLite
    -0.60
    moveToFirst
    -0.59
     AssemblyTitle
    -0.55
    تقاوى
    -0.55
     laborales
    -0.54
     виправивши
    -0.53
    RegressionTest
    -0.52
    POSITIVE LOGITS
    Rptr
    0.62
     vPvB
    0.56
    ælde
    0.54
    رشف
    0.54
    __).
    0.52
    lccn
    0.51
    ymal
    0.51
    MultipartFile
    0.48
    TagMode
    0.47
    tdessen
    0.47
    Activations Density 2.074%

    No Known Activations