© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14073
    Prev
    Next
    INDEX
    Explanations

    the word "things" and similar adverbs of degree, such as "differently", "somewhat", and "further"

    oai_token-act-pair · gemini-2.0-flash

    things

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    GraphicsUnit
    -0.67
     VIAF
    -0.49
    WriteAttribute
    -0.48
     rayures
    -0.47
     oreilles
    -0.46
     diamants
    -0.45
    入れた
    -0.44
     käyttää
    -0.44
    انيف
    -0.43
    findpost
    -0.43
    POSITIVE LOGITS
     &_
    0.68
    pyplot
    0.64
    ArrowToggle
    0.62
     Things
    0.60
    tanleria
    0.58
     ujednoznacz
    0.58
     שוליים
    0.57
     kasarigan
    0.57
    Things
    0.57
    cristo
    0.56
    Activations Density 1.102%

    No Known Activations