© 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. 10419
    Prev
    Next
    INDEX
    Explanations

    job postings, especially for nurses and related medical staff.

    oai_token-act-pair · gemini-2.0-flash

    work shifts and hours

    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
     Days
    -1.01
     week
    -1.00
     days
    -0.98
     day
    -0.96
    Days
    -0.96
     Day
    -0.93
    Day
    -0.93
    DAYS
    -0.93
    DAY
    -0.92
     DAYS
    -0.92
    POSITIVE LOGITS
     autorytatywna
    0.80
    writeFieldEnd
    0.57
    BASEPATH
    0.55
     الاطلاع
    0.54
     onCreateView
    0.50
    Hauptartikel
    0.49
    \{\\
    0.49
    illère
    0.48
     المعرف
    0.48
     Biar
    0.47
    Activations Density 1.818%

    No Known Activations