© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2674
    Prev
    Next
    INDEX
    Explanations

    road and highway information including route numbers and distances

    oai_token-act-pair · gemini-2.0-flash

    Locations, distances, code

    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
    허
    -0.61
     ویکی‌پدی
    -0.60
    essment
    -0.57
    IContainer
    -0.56
     &___
    -0.55
    okovic
    -0.53
    saraba
    -0.53
    Ƚ
    -0.52
    tagHelperRunner
    -0.51
     незавершена
    -0.51
    POSITIVE LOGITS
     noDo
    0.59
    SharedCtor
    0.56
     Monfieur
    0.54
     intStringLen
    0.53
     réus
    0.52
    Distribuzione
    0.52
    resor
    0.51
    forRoot
    0.51
    ASSOCI
    0.50
     pleaſure
    0.49
    Activations Density 0.127%

    No Known Activations