© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5450
    Prev
    Next
    INDEX
    Explanations

    punctuation and ordinal words in political documents

    oai_token-act-pair · gemini-2.0-flash

    patterns that resemble programming or technical terms

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     ***!
    -0.64
     cứ
    -0.55
    zenten
    -0.53
    fml
    -0.52
    rega
    -0.50
    cein
    -0.50
     lateinit
    -0.50
    dillo
    -0.50
     sekali
    -0.49
     Doo
    -0.49
    POSITIVE LOGITS
    IntoConstraints
    0.66
     Shakspeare
    0.60
     ftate
    0.59
     JpaRepository
    0.58
    IGraphics
    0.57
     fince
    0.57
    DockStyle
    0.57
    UpInside
    0.56
     XNUMX
    0.53
     ujednoznacz
    0.52
    Activations Density 1.962%

    No Known Activations