© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 13057
    Prev
    Next
    INDEX
    Explanations

    the word "staff" or things associated with staffing, like a unit

    oai_token-act-pair · gemini-2.0-flash

    staff

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     staff
    -2.47
    Staff
    -2.34
     Staff
    -2.30
    staff
    -2.23
     STAFF
    -2.08
    STAFF
    -1.91
     staffs
    -1.91
     staffers
    -1.43
     staf
    -1.34
     staffing
    -1.20
    POSITIVE LOGITS
    ocyan
    0.47
    限り
    0.45
     assassin
    0.44
     Marching
    0.44
    šit
    0.44
    Ứng
    0.42
     suon
    0.42
     Tread
    0.41
    ulative
    0.41
     chale
    0.41
    Activations Density 2.111%

    No Known Activations