© 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. 15975
    Prev
    Next
    INDEX
    Explanations

    advice and reassurance

    oai_token-act-pair · gemini-2.0-flash

    peace

    np_max-act-logits · gemini-2.0-flash
    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
     fédé
    -0.51
     columnIndex
    -0.49
    createQuery
    -0.48
    URLException
    -0.48
    NASDAQ
    -0.47
    @[+][
    -0.47
    HasForeignKey
    -0.47
     jagung
    -0.47
    UNRELATED
    -0.46
    dozer
    -0.45
    POSITIVE LOGITS
     peace
    2.34
    peace
    1.90
     Peace
    1.80
    Peace
    1.76
     PEACE
    1.74
    PEACE
    1.59
     paix
    1.28
     piece
    1.27
     Piece
    1.14
     peaceful
    1.11
    Activations Density 0.854%

    No Known Activations