© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 3-GEMMASCOPE-TRANSCODER-16K
    4. 4391
    Prev
    Next
    INDEX
    Explanations

    the keyword "final" in Java code

    oai_token-act-pair · gemini-2.0-flash

    final

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    final
    -1.15
     final
    -1.02
    Final
    -0.91
    UnusedPrivate
    -0.85
     Final
    -0.79
     FINAL
    -0.77
    <bos>
    -0.73
    FINAL
    -0.71
    finals
    -0.69
    finally
    -0.67
    POSITIVE LOGITS
    migrationBuilder
    0.61
    __(/*!
    0.56
    isContained
    0.53
    ingtones
    0.51
    anganese
    0.49
    Carriera
    0.49
    setLayoutManager
    0.49
    MockMvc
    0.47
     esternos
    0.46
    amaño
    0.46
    Activations Density 0.179%

    No Known Activations