© 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. 5266
    Prev
    Next
    INDEX
    Explanations

    stack traces, especially from Android apps

    oai_token-act-pair · gemini-2.0-flash

    Programming code/errors

    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
    bootstrapcdn
    -0.73
    ValueStyle
    -0.68
     Shakspeare
    -0.65
     ویکی‌پدی
    -0.57
    twimg
    -0.55
     Chriftian
    -0.54
     enkelte
    -0.53
     chrétien
    -0.52
     Efq
    -0.52
     itſelf
    -0.52
    POSITIVE LOGITS
     ActionListener
    0.61
     AttributeSet
    0.60
    catore
    0.50
     insuffisamment
    0.50
    artifactId
    0.49
    aung
    0.49
    GenerationType
    0.49
    vacy
    0.49
    ISING
    0.48
    tificate
    0.48
    Activations Density 0.018%

    No Known Activations