© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 5141
    Prev
    Next
    INDEX
    Explanations

    words related to an interview or job application

    oai_token-act-pair · gemini-2.0-flash

    interview

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    endpush
    -0.64
    ManagedBean
    -0.62
    FileDialog
    -0.56
    setContentView
    -0.52
    setupUi
    -0.49
    enment
    -0.49
    StoryboardSegue
    -0.49
    tvguidetime
    -0.48
    badlogic
    -0.46
    alamualaikum
    -0.46
    POSITIVE LOGITS
    دانشنامهٔ
    0.63
    NameInMap
    0.60
     Италијани
    0.60
    protoimpl
    0.54
     Kerja
    0.53
     overla
    0.52
     nakalista
    0.51
     renovables
    0.50
     Zeller
    0.50
     Taktlose
    0.50
    Activations Density 0.388%

    No Known Activations