© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14637
    Prev
    Next
    INDEX
    Explanations

    instances of the word "half"

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "half"

    np_token-act-pair-logits · gpt-4o-mini

    half

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    verwijspagina
    -0.66
    expandindo
    -0.64
     unknownFields
    -0.59
    },{
    -0.57
     ostavi
    -0.57
     gyhoeddwyd
    -0.57
    lapsingToolbar
    -0.57
     setuptools
    -0.56
     StatefulWidget
    -0.55
    WebElementEntity
    -0.54
    POSITIVE LOGITS
    Elf
    0.52
    ssch
    0.48
    orphaned
    0.47
    tizen
    0.47
     listener
    0.46
    üch
    0.46
    hpur
    0.45
    jmp
    0.44
    complexType
    0.44
    ViewChild
    0.44
    Activations Density 2.368%

    No Known Activations