© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4444
    Prev
    Next
    INDEX
    Explanations

    HTML table row tags

    oai_token-act-pair · gemini-2.0-flash

    tokens related to code or markup

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

    Table row tag or "There"

    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
    tagHelperRunner
    -0.82
     linkovi
    -0.79
    IsContent
    -0.73
    IBarButtonItem
    -0.73
    principalColumn
    -0.71
    InvalidProtocol
    -0.71
    ########.
    -0.70
     المعيارى
    -0.70
    EndTag
    -0.70
     AssemblyVersion
    -0.70
    POSITIVE LOGITS
     <
    0.45
    <
    0.44
    tuous
    0.41
     Rule
    0.40
    ืน
    0.39
    {#
    0.39
     Sequence
    0.38
    RegressionTest
    0.38
    Prosec
    0.38
    <*
    0.38
    Activations Density 0.332%

    No Known Activations