© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10264
    Prev
    Next
    INDEX
    Explanations

    the word "be" preceded or followed by modal verbs or auxiliaries

    oai_token-act-pair · gemini-2.0-flash

    be

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    Referências
    -0.45
     sejauh
    -0.44
    ệnh
    -0.43
     pungkas
    -0.43
     abordagem
    -0.42
    Catégorie
    -0.41
     те
    -0.41
    丁目
    -0.41
     penerima
    -0.41
     prestazioni
    -0.40
    POSITIVE LOGITS
     slept
    0.78
     enjoyed
    0.77
     availed
    0.76
     uſed
    0.74
    CppMethod
    0.73
     betweenstory
    0.73
     relied
    0.71
     exercised
    0.71
     utilized
    0.70
     ridden
    0.70
    Activations Density 0.877%

    No Known Activations