© 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. 14515
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to data persistence and database interaction in software.

    oai_token-act-pair · gemini-2.0-flash

    technical terms or keywords in algorithmic contexts

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

    code and data

    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
     AssemblyProduct
    -0.62
    uxxxx
    -0.59
     Investigaciones
    -0.49
    istique
    -0.48
     Uranus
    -0.47
    ագրություններ
    -0.46
    titleMargin
    -0.46
    Generating
    -0.46
    ">//
    -0.44
    psies
    -0.42
    POSITIVE LOGITS
     BorderSide
    0.57
    Rè
    0.56
    orphic
    0.54
    CodeAttribute
    0.54
     logic
    0.52
     compi
    0.52
    gran
    0.51
     Schell
    0.51
    ght
    0.50
    opa
    0.50
    Activations Density 7.395%

    No Known Activations