© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8056
    Prev
    Next
    INDEX
    Explanations

    square brackets, sometimes near words indicating actions ("performing", "tyrosine", "phosphatase")

    oai_token-act-pair · gemini-2.0-flash

    bracket token

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     }}"></
    -0.72
    CloseOperation
    -0.69
     Réponses
    -0.65
     FetchType
    -0.61
     onCreateView
    -0.58
     chofe
    -0.56
    HasAnnotation
    -0.56
    XmlAccessorType
    -0.55
     }</
    -0.55
    منابع
    -0.55
    POSITIVE LOGITS
     الحره
    0.65
     كومونز
    0.57
    kmale
    0.53
    الإنجليزية
    0.50
    ulos
    0.49
     render
    0.49
    복
    0.48
    wh
    0.48
     command
    0.48
     float
    0.48
    Activations Density 2.469%

    No Known Activations