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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 452
    Prev
    Next
    INDEX
    Explanations

    words related to employees, their experiences, and management

    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_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
    Not in Any Lists

    No Comments

    Negative Logits
    WebServlet
    -0.54
     samarbeid
    -0.52
     ©️
    -0.52
     förr
    -0.50
     Chances
    -0.50
    ConstraintLayout
    -0.48
    atai
    -0.48
    #__
    -0.48
    responseBody
    -0.47
    ǔ
    -0.47
    POSITIVE LOGITS
     виправивши
    0.68
    personal
    0.63
     personal
    0.63
    Personal
    0.60
     henkil
    0.57
     Personal
    0.57
     personally
    0.56
     سكانية
    0.55
     personale
    0.55
    Portály
    0.55
    Activations Density 1.979%

    No Known Activations