© 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. 2853
    Prev
    Next
    INDEX
    Explanations

    the word "recent" and words appearing near it.

    oai_token-act-pair · 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
    TagHelper
    -0.76
    __'
    -0.53
    openSession
    -0.52
    LabelTagHelper
    -0.47
    LayoutStyle
    -0.46
    clientWidth
    -0.45
    chrän
    -0.45
     Directorate
    -0.44
    awaiter
    -0.44
    ICIAN
    -0.44
    POSITIVE LOGITS
    ValueStyle
    0.84
    TargetException
    0.74
     propOrder
    0.70
     disambiguazione
    0.59
     months
    0.58
    MemoryWarning
    0.56
    Gambas
    0.56
     BitmapFactory
    0.56
     Baillargeon
    0.54
     years
    0.53
    Activations Density 0.908%

    No Known Activations