© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10952
    Prev
    Next
    INDEX
    Explanations

    the word "computer", sometimes in related contexts such as "desk" or "negatively"

    oai_token-act-pair · gemini-2.0-flash

    computer

    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
    chnet
    -0.64
    IndentedString
    -0.62
     zucchero
    -0.60
    LGBT
    -0.58
     condoms
    -0.58
     singolo
    -0.58
    TimerTask
    -0.58
     getItemId
    -0.57
     iprot
    -0.57
    WGS
    -0.57
    POSITIVE LOGITS
    MENAFN
    0.86
    ställning
    0.73
    czegó
    0.71
    CrossRef
    0.71
    ficulty
    0.70
    pecially
    0.69
    toor
    0.68
    منابع
    0.66
    hematical
    0.66
     hot
    0.66
    Activations Density 1.352%

    No Known Activations