© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13954
    Prev
    Next
    INDEX
    Explanations

    medical terminology and scientific measurements

    oai_token-act-pair · gemini-2.0-flash

    measurement

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    -0.73
    CodeAttribute
    -0.72
    webElementXpaths
    -0.69
     resourceCulture
    -0.65
    inerja
    -0.62
     يتيمه
    -0.61
    hyrchwyd
    -0.60
    DockStyle
    -0.59
    Hearing
    -0.59
    zegor
    -0.58
    POSITIVE LOGITS
     determination
    1.22
     Determination
    1.06
    determin
    1.03
    determination
    1.01
    Determination
    1.01
     measurement
    1.00
     measurements
    0.96
     determinations
    0.94
     determined
    0.94
     Determin
    0.94
    Activations Density 5.307%

    No Known Activations