© 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. 10719
    Prev
    Next
    INDEX
    Explanations

    words and names associated with politics and religion

    oai_token-act-pair · gemini-2.0-flash

    progres

    np_max-act-logits · 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
     Jefus
    -0.80
     pinulongan
    -0.79
     myſelf
    -0.77
     Monfieur
    -0.73
     commerciales
    -0.72
     EconPapers
    -0.72
     Reſ
    -0.71
     himſelf
    -0.69
     Majefty
    -0.68
     démocr
    -0.67
    POSITIVE LOGITS
    lies
    0.60
    aries
    0.58
    mies
    0.57
    dies
    0.57
    rds
    0.55
    els
    0.54
    ies
    0.54
    als
    0.52
    ताओं
    0.52
    ents
    0.51
    Activations Density 1.799%

    No Known Activations