© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9098
    Prev
    Next
    INDEX
    Explanations

    words related to job advancement or being moved to a higher or lower level position

    oai_token-act-pair · gemini-2.0-flash

    promotion/demotion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    截
    -0.55
     endblock
    -0.55
    퀘
    -0.55
     most
    -0.53
    wpi
    -0.52
    quest
    -0.51
    mutter
    -0.51
    \}^{
    -0.51
     question
    -0.49
    yra
    -0.49
    POSITIVE LOGITS
     promotion
    1.04
     Promoted
    1.02
     Promotion
    0.98
    Promotion
    0.96
    promotion
    0.96
    promoted
    0.94
     promos
    0.92
     promoted
    0.91
    PROMOTED
    0.91
    promo
    0.88
    Activations Density 0.313%

    No Known Activations