© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12559
    Prev
    Next
    INDEX
    Explanations

    information related to publications and educational history

    oai_token-act-pair · gemini-2.0-flash

    citations or biographies

    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
     mergeFrom
    -0.70
    esgue
    -0.70
    AddTagHelper
    -0.69
     StatefulWidget
    -0.69
    setVerticalGroup
    -0.63
     مشين
    -0.62
    ModelAdmin
    -0.62
     MonoBehaviour
    -0.60
     calendriers
    -0.59
    windowFixed
    -0.59
    POSITIVE LOGITS
     Pleasure
    0.50
     fatica
    0.48
    Largeur
    0.47
    éte
    0.47
    кість
    0.46
    पया
    0.46
     bäst
    0.44
    aimer
    0.44
     bruising
    0.43
     privilégi
    0.43
    Activations Density 1.873%

    No Known Activations