© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7863
    Prev
    Next
    INDEX
    Explanations

    scientific and technical jargon used in research papers

    oai_token-act-pair · gemini-2.0-flash

    crust/geological

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    rungsseite
    -0.75
    出版年
    -0.68
     Administrativna
    -0.66
     Roskov
    -0.66
    Tembelea
    -0.65
     GenerationType
    -0.62
    Autoritní
    -0.61
     autorytatywna
    -0.59
     newOwner
    -0.59
    inigung
    -0.57
    POSITIVE LOGITS
     miner
    0.56
     crust
    0.56
    plate
    0.52
    crust
    0.48
    crat
    0.48
     crater
    0.46
     subsurface
    0.46
     PLL
    0.46
     mag
    0.46
    CppMethod
    0.46
    Activations Density 1.057%

    No Known Activations