© 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. 2694
    Prev
    Next
    INDEX
    Explanations

    the word 'invention' or grammatical constructs typical of an invention disclosure

    oai_token-act-pair · gemini-2.0-flash

    say "relates"

    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
     pinulongan
    -0.67
    TestTools
    -0.54
     चुनें
    -0.50
    Rhestr
    -0.50
    InstrumentedTest
    -0.50
    Geplaatst
    -0.49
    setContentType
    -0.47
     végét
    -0.47
     móveis
    -0.46
    LookAnd
    -0.45
    POSITIVE LOGITS
     relates
    1.48
     relate
    1.48
     refer
    1.42
     pertains
    1.41
     referring
    1.35
     refers
    1.33
     pertain
    1.32
     riguarda
    1.26
    refer
    1.25
     refere
    1.23
    Activations Density 2.525%

    No Known Activations