© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6023
    Prev
    Next
    INDEX
    Explanations

    fragments of words ending in "eder" or "fed"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    Late
    -0.74
     Late
    -0.71
     late
    -0.68
     LATE
    -0.68
     senare
    -0.64
    LATE
    -0.63
    rungsseite
    -0.60
     spät
    -0.59
     LATER
    -0.58
    Derbyniad
    -0.58
    POSITIVE LOGITS
    MigrationBuilder
    0.73
     federal
    0.68
    WebServlet
    0.66
    FED
    0.61
     FED
    0.60
    فحة
    0.60
    hene
    0.59
    Feder
    0.57
     Feder
    0.57
    Fed
    0.56
    Activations Density 0.527%

    No Known Activations