© 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
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6689
    Prev
    Next
    INDEX
    Explanations

    the keyword "private" in code

    oai_token-act-pair · gemini-2.0-flash

    private

    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
    OrBuilder
    -0.59
     viewDidLoad
    -0.57
     econô
    -0.57
    UnknownFields
    -0.57
     voudrais
    -0.56
     dilan
    -0.55
     zeichnet
    -0.54
    ViewFeatures
    -0.54
    StructEnd
    -0.54
    woordig
    -0.53
    POSITIVE LOGITS
    <bos>
    1.11
    曖昧さ回避
    0.57
    WEBPACK
    0.52
    !(:
    0.50
     muualla
    0.50
     kasarigan
    0.49
    ValueStyle
    0.48
    исленность
    0.47
    amente
    0.46
    verde
    0.46
    Activations Density 0.043%

    No Known Activations