© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9530
    Prev
    Next
    INDEX
    Explanations

    snippets from source code that contain the word "empty" or a similar concept relating to emptiness

    oai_token-act-pair · gemini-2.0-flash

    empty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     empty
    -2.48
     Empty
    -2.34
    empty
    -2.30
    Empty
    -2.16
     EMPTY
    -1.69
     emptied
    -1.58
     leeren
    -1.55
    EMPTY
    -1.54
     vacant
    -1.42
     vacía
    -1.40
    POSITIVE LOGITS
    الحياه
    0.68
    HtmlAttribute
    0.63
    XmlRootElement
    0.60
    pektor
    0.58
    FOOTNOTES
    0.58
    DataMember
    0.58
    ofern
    0.56
    olume
    0.55
    ViewFeatures
    0.55
    ("#{
    0.55
    Activations Density 12.441%

    No Known Activations