© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14803
    Prev
    Next
    INDEX
    Explanations

    scientific measurements and study design terminology

    oai_token-act-pair · gemini-2.0-flash

    Scientific/medical data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    ,
    -0.56
    .
    -0.53
    :
    -0.48
     (
    -0.48
     program
    -0.47
     $
    -0.47
     "
    -0.46
     '
    -0.45
     local
    -0.44
     ing
    -0.44
    POSITIVE LOGITS
    <bos>
    1.55
    __':
    1.02
    Билгалдахарш
    1.00
     Jefus
    0.99
    RegressionTest
    0.98
     Monfieur
    0.98
     CreateTagHelper
    0.96
    SharedCtor
    0.96
    ThroughAttribute
    0.96
     initComponents
    0.94
    Activations Density 2.177%

    No Known Activations