© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11898
    Prev
    Next
    INDEX
    Explanations

    the word "discipline" and words with generally positive connotations.

    oai_token-act-pair · gemini-2.0-flash

    punishment and control

    np_max-act · gemini-2.0-flash

    discipline

    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_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    awtextra
    -1.06
    onViewCreated
    -1.05
     discipline
    -0.99
     Discipline
    -0.91
    ArgsConstructor
    -0.88
    setupUi
    -0.87
    Discipline
    -0.85
     disciplina
    -0.85
    discipline
    -0.84
    NewUrlParser
    -0.82
    POSITIVE LOGITS
    Enders
    0.41
     millón
    0.41
     liked
    0.39
     ({
    0.38
    IFC
    0.38
     beira
    0.37
    lanması
    0.37
    array
    0.36
    تا
    0.35
    asyonu
    0.35
    Activations Density 1.190%

    No Known Activations