© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5327
    Prev
    Next
    INDEX
    Explanations

    a mix of words used in scientific studies involving statistical analysis, pharmaceutical chemistry, and medical terminology

    oai_token-act-pair · gemini-2.0-flash

    Econometrics and research papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     biographer
    -0.69
     witches
    -0.69
    ExecuteReader
    -0.68
     nebula
    -0.65
     galleries
    -0.64
     cords
    -0.64
     chords
    -0.63
     astronomer
    -0.63
     spectra
    -0.63
     weavers
    -0.63
    POSITIVE LOGITS
     prochaines
    0.50
     tartalomajánló
    0.41
     stället
    0.38
     culturelles
    0.38
     devaient
    0.35
     attentes
    0.35
     mauvaises
    0.35
     vérit
    0.34
    acy
    0.33
     dernières
    0.33
    Activations Density 5.646%

    No Known Activations