© 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. 12807
    Prev
    Next
    INDEX
    Explanations

    instances of the word "a" following words like "have", "has", or "an"

    oai_token-act-pair · gemini-2.0-flash

    a

    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
     An
    -0.52
    y
    -0.51
     No
    -0.51
    '
    -0.49
     and
    -0.49
     no
    -0.48
    .
    -0.47
    no
    -0.47
     an
    -0.47
    p
    -0.47
    POSITIVE LOGITS
    IntoConstraints
    1.07
     AssemblyCulture
    1.02
    URLException
    0.99
    expandindo
    0.96
    AddTagHelper
    0.94
    MigrationBuilder
    0.92
    CloseOperation
    0.91
     lenker
    0.91
    MemoryWarning
    0.90
     GenerationType
    0.86
    Activations Density 0.497%

    No Known Activations