© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 16024
    Prev
    Next
    INDEX
    Explanations

    text concerning mathematical or numerical comparisons and questions

    oai_token-act-pair · gemini-2.0-flash

    Comparing numbers

    np_max-act-logits · gemini-2.0-flash

    say "is/bigger/greater"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     AssemblyCulture
    -0.73
     Normdatei
    -0.70
    EndGlobalSection
    -0.69
    LayoutConstraint
    -0.68
    featureID
    -0.66
     pageContext
    -0.64
    FieldBuilder
    -0.63
     >=",
    -0.61
    ViewFeatures
    -0.57
    róleo
    -0.57
    POSITIVE LOGITS
    larak
    0.48
     dAtA
    0.47
    __.__
    0.41
    czegó
    0.41
    IConfiguration
    0.40
    Repeated
    0.40
    hány
    0.40
     $\
    0.40
     faltar
    0.40
    ОВ
    0.40
    Activations Density 5.991%

    No Known Activations