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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 4737
    Prev
    Next
    INDEX
    Explanations

    language related to government pensions and financial contributions

    oai_token-act-pair · gemini-2.0-flash

    terms related to employees or staff

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

    employees

    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
     betweenstory
    -0.71
     ब्रेकडाउन
    -0.66
    醐
    -0.60
    UseVisualStyle
    -0.59
    ftagPool
    -0.56
    存于互联网档案馆
    -0.54
    InvalidProtocol
    -0.54
    TagHelper
    -0.54
    DoubleQuotes
    -0.52
    الدراسه
    -0.51
    POSITIVE LOGITS
     employee
    0.81
     employees
    0.77
     staff
    0.77
     Staff
    0.76
    Staff
    0.73
     civil
    0.72
     teachers
    0.68
    employee
    0.68
     Civil
    0.68
     Employees
    0.68
    Activations Density 2.366%

    No Known Activations