© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13220
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to performing a job or occupation

    oai_token-act-pair · gemini-2.0-flash

    work

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     work
    -0.67
     works
    -0.53
     worked
    -0.52
    <bos>
    -0.50
    ciuto
    -0.50
    Works
    -0.48
     טוב
    -0.45
    ute
    -0.45
     term
    -0.45
     eneste
    -0.44
    POSITIVE LOGITS
     Roskov
    1.00
     AssemblyProduct
    0.90
    +#+#
    0.85
     '\\;'
    0.81
     ModelExpression
    0.81
    存于互联网档案馆
    0.71
     PLWABN
    0.70
    WebVitals
    0.69
     nahilalakip
    0.69
     GeoNames
    0.68
    Activations Density 0.634%

    No Known Activations