© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11325
    Prev
    Next
    INDEX
    Explanations

    words pertaining to a person's job, education, or career, and slightly to politics, sports or academia

    oai_token-act-pair · gemini-2.0-flash

    careers and schools

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    Fitment
    -0.57
     spd
    -0.55
    HomeAsUpEnabled
    -0.53
    cales
    -0.48
    ll
    -0.47
    BrowserModule
    -0.46
    )=>{
    -0.46
    配
    -0.46
    GoogleApiClient
    -0.46
     Package
    -0.45
    POSITIVE LOGITS
    Portail
    0.68
    Clik
    0.68
     ujednoznacz
    0.66
     linkovi
    0.65
     nahilalakip
    0.64
    Искәрмәләр
    0.60
    LookAnd
    0.60
    TagMode
    0.57
    (!__
    0.53
    Chham
    0.53
    Activations Density 10.711%

    No Known Activations