© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11554
    Prev
    Next
    INDEX
    Explanations

    words associated with groups of people and hierarchies.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    DockStyle
    -0.99
    elemField
    -0.70
    Geplaatst
    -0.69
    saraba
    -0.68
    rungsseite
    -0.66
    XmlAccessType
    -0.65
     Taktlose
    -0.65
     CURIAM
    -0.65
    جمعیت
    -0.63
    Gambas
    -0.63
    POSITIVE LOGITS
     because
    0.49
     Big
    0.45
     делать
    0.45
    grès
    0.45
    لط
    0.44
    ors
    0.43
     cause
    0.43
     may
    0.43
    because
    0.43
     did
    0.42
    Activations Density 13.047%

    No Known Activations