© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15241
    Prev
    Next
    INDEX
    Explanations

    words related to academic studies and research trials.

    oai_token-act-pair · gemini-2.0-flash

    Occupations

    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
     EconPapers
    -0.72
    awtextra
    -0.67
    twimg
    -0.63
    Външни
    -0.61
     transfieras
    -0.58
     TestBed
    -0.58
     跳转至
    -0.57
     defaultstate
    -0.57
    fromnode
    -0.57
     initComponents
    -0.56
    POSITIVE LOGITS
     Officer
    0.54
     kasarigan
    0.52
     Governor
    0.47
    Officer
    0.47
     Writer
    0.47
    ритори
    0.46
     Lawyer
    0.46
     Doctors
    0.46
     Officers
    0.45
     pères
    0.44
    Activations Density 6.676%

    No Known Activations