© 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. 12509
    Prev
    Next
    INDEX
    Explanations

    varied, reacting to questions posed to the reader, relationship difficulties, the political framing of "Democrats", and architecture in software

    oai_token-act-pair · gemini-2.0-flash

    because

    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
    bootstrapcdn
    -0.77
    abestanden
    -0.77
    ViewImports
    -0.72
    ValueGeneration
    -0.71
    GeneratedValue
    -0.69
    routeProvider
    -0.66
     AssemblyProduct
    -0.60
    zerű
    -0.59
    presto
    -0.59
    rungsseite
    -0.59
    POSITIVE LOGITS
     because
    2.88
    because
    2.66
    Because
    2.55
     porque
    2.47
     Because
    2.45
     BECAUSE
    2.25
    porque
    2.09
     karena
    2.02
     perché
    2.02
     Porque
    1.99
    Activations Density 3.600%

    No Known Activations