© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12964
    Prev
    Next
    INDEX
    Explanations

    job advertisement postings and negative traits of people

    oai_token-act-pair · gemini-2.0-flash

    sales-related terms

    np_token-act-pair-logits · gpt-4o-mini

    sales

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ￣)
    -0.53
     MonoBehaviour
    -0.50
    ibouti
    -0.48
     ويكيميديا
    -0.47
     متعلقه
    -0.47
    ::__
    -0.46
    behaved
    -0.45
     Molière
    -0.45
    发表于
    -0.44
    rolid
    -0.43
    POSITIVE LOGITS
     sales
    1.50
     Sales
    1.39
    Sales
    1.34
    sales
    1.34
     SALES
    1.24
    SALES
    1.20
     salespeople
    1.09
     salesman
    1.04
     ventas
    1.03
     salesmen
    1.01
    Activations Density 1.492%

    No Known Activations