© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 264
    Prev
    Next
    INDEX
    Explanations

    the word "is" relative to other words

    oai_token-act-pair · gemini-2.0-flash

    to be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    pushFollow
    -0.60
    WebElementEntity
    -0.57
    WindowConstants
    -0.56
    RenderAtEndOf
    -0.56
     peacock
    -0.55
     ostavi
    -0.54
    SPATH
    -0.54
     ResourceManager
    -0.54
     iArr
    -0.54
    rąg
    -0.53
    POSITIVE LOGITS
     الوطنيه
    0.56
     собой
    0.54
     دیکھیے
    0.52
    లాలు
    0.52
    Erreferentziak
    0.51
     an
    0.51
     fiind
    0.50
     AssemblyVersion
    0.50
     vậy
    0.50
    MemoryWarning
    0.49
    Activations Density 2.729%

    No Known Activations