© 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. 10709
    Prev
    Next
    INDEX
    Explanations

    lines of code that begin with the @ symbol

    oai_token-act-pair · gemini-2.0-flash

    text starting with '@'

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

    @

    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
    ː
    -0.48
     Dum
    -0.45
    migrationBuilder
    -0.44
    ৎ
    -0.43
     Pir
    -0.42
     cubes
    -0.41
    zot
    -0.41
    mont
    -0.41
    des
    -0.40
    air
    -0.40
    POSITIVE LOGITS
     resourceCulture
    0.85
    Sklici
    0.78
     AssemblyCulture
    0.75
     Exacts
    0.74
    RegressionTest
    0.72
    Kjelder
    0.71
    abestanden
    0.67
    లాలు
    0.66
    Override
    0.65
    DoubleQuotes
    0.64
    Activations Density 0.180%

    No Known Activations