© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8748
    Prev
    Next
    INDEX
    Explanations

    words that evoke a sense of purity, authenticity, or lack of artificiality.

    oai_token-act-pair · gemini-2.0-flash

    natural

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    łaszcza
    -0.59
    FailureListener
    -0.54
    PhysRev
    -0.54
     față
    -0.52
     <",
    -0.49
     urme
    -0.46
     close
    -0.44
     aceea
    -0.44
    CompleteListener
    -0.44
     scurt
    -0.43
    POSITIVE LOGITS
    webElementXpaths
    0.81
    sizeCache
    0.77
     cherchés
    0.67
    tvguidetime
    0.65
    GEBURTSDATUM
    0.63
    ViewFeatures
    0.62
     estekak
    0.61
    reportWebVitals
    0.60
    UserScript
    0.59
    DMETHOD
    0.59
    Activations Density 1.265%

    No Known Activations