© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11626
    Prev
    Next
    INDEX
    Explanations

    code syntax related to database updates

    oai_token-act-pair · gemini-2.0-flash

    code and database update operations

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

    SQL database commands

    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
     autorytatywna
    -0.64
    PyExc
    -0.63
     EClass
    -0.61
    abetes
    -0.60
     Réponses
    -0.60
    +:+
    -0.59
    LayoutStyle
    -0.56
    RegressionTest
    -0.55
     <>",
    -0.54
     Signalez
    -0.54
    POSITIVE LOGITS
    TabView
    0.48
    hee
    0.44
     knife
    0.43
     sklo
    0.43
     Loa
    0.43
    knife
    0.41
    artifactId
    0.41
    olian
    0.41
    HostException
    0.41
     Bühne
    0.41
    Activations Density 0.779%

    No Known Activations