© 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. 10493
    Prev
    Next
    INDEX
    Explanations

    the word "got" (often followed by prepositions), but not always, and sometimes correlates with personal anecdotes

    oai_token-act-pair · gemini-2.0-flash

    got

    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
     still
    -0.69
     always
    -0.57
    still
    -0.54
     finally
    -0.49
     definitely
    -0.48
     sempre
    -0.46
     toujours
    -0.46
     never
    -0.42
    always
    -0.42
     often
    -0.42
    POSITIVE LOGITS
     ProtoMessage
    0.84
    WebVitals
    0.82
    oredCriteria
    0.82
     Мексичка
    0.78
    EndGlobalSection
    0.77
    :✨
    0.75
    uação
    0.75
    DataAnnotations
    0.75
    يكب
    0.75
    цезда
    0.75
    Activations Density 0.946%

    No Known Activations