© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13881
    Prev
    Next
    INDEX
    Explanations

    somewhat common words and phrases that appear in a variety of contexts

    oai_token-act-pair · gemini-2.0-flash

    Breaking

    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
    出版年
    -0.64
    secuencias
    -0.62
    oriques
    -0.57
    [++
    -0.54
     Missed
    -0.54
     DialogInterface
    -0.54
    Missed
    -0.52
     textStatus
    -0.52
     parteci
    -0.52
    endwhile
    -0.52
    POSITIVE LOGITS
     breakdown
    1.11
     breaking
    1.05
     crumbling
    1.03
    breaking
    1.00
     crumble
    0.96
     break
    0.95
     cracking
    0.94
     breakdowns
    0.93
     disintegration
    0.93
     broke
    0.91
    Activations Density 3.856%

    No Known Activations