© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3991
    Prev
    Next
    INDEX
    Explanations

    words or phrases centered around consent, opting in, and whether something is voluntary or required

    oai_token-act-pair · gemini-2.0-flash

    Optionality

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    TypedDataSet
    -0.79
     ModelExpression
    -0.68
    CodeAttribute
    -0.68
    AnimationsModule
    -0.68
     propOrder
    -0.67
    ]<<"
    -0.66
    PerformLayout
    -0.66
    awtextra
    -0.62
    Controllo
    -0.62
    addCriterion
    -0.60
    POSITIVE LOGITS
     optional
    1.76
     Option
    1.56
     voluntary
    1.47
     option
    1.45
    Optional
    1.41
    optional
    1.41
     Optional
    1.41
    option
    1.41
    Option
    1.39
     freiw
    1.29
    Activations Density 1.517%

    No Known Activations