© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5805
    Prev
    Next
    INDEX
    Explanations

    the terms 'account', 'task', 'Game', 'chat', 'page', 'graphic', and 'family', suggesting it looks for code syntax related to page-task structure, graphical and game-related variables, family assignments, and accounts

    oai_token-act-pair · gemini-2.0-flash

    coding configuration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -1.37
     Мексичка
    -1.16
    endphp
    -1.11
    Билгалдахарш
    -0.99
    ThroughAttribute
    -0.98
     intptr
    -0.97
     CreateTagHelper
    -0.96
    
    -0.94
     дописавши
    -0.93
    GEBURTSDATUM
    -0.93
    POSITIVE LOGITS
     type
    0.55
     
    0.55
     new
    0.54
     base
    0.53
     _
    0.52
    yn
    0.52
     original
    0.51
    yp
    0.50
    ci
    0.49
     &
    0.49
    Activations Density 0.885%

    No Known Activations