© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10750
    Prev
    Next
    INDEX
    Explanations

    words related to specific professions

    oai_token-act-pair · gemini-2.0-flash

    coding or patients

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     виправивши
    -0.98
     ExecuteAsync
    -0.82
    +#+#
    -0.79
     esportivo
    -0.78
    mybatisplus
    -0.77
     defaultstate
    -0.77
    endpush
    -0.75
     photolibrary
    -0.73
    SequentialGroup
    -0.72
     initComponents
    -0.70
    POSITIVE LOGITS
    <bos>
    0.63
     make
    0.62
     be
    0.58
     να
    0.55
     take
    0.55
     $
    0.53
     get
    0.52
     keep
    0.50
    ',$
    0.49
     bring
    0.49
    Activations Density 3.434%

    No Known Activations