© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11509
    Prev
    Next
    INDEX
    Explanations

    the verb "defend" and its inflections

    oai_token-act-pair · gemini-2.0-flash

    defends/ends

    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
    heiser
    -0.56
     trời
    -0.52
    Expedia
    -0.49
    TintMode
    -0.49
    etration
    -0.48
    istoitu
    -0.47
     dob
    -0.47
    zī
    -0.46
    bla
    -0.46
     Accesat
    -0.45
    POSITIVE LOGITS
     فريبيس
    0.91
     indisponible
    0.90
    Autoritní
    0.81
    ArgsConstructor
    0.79
    SharedDtor
    0.69
     Defend
    0.66
    runApp
    0.66
     InputDecoration
    0.65
     Vau
    0.65
     مشين
    0.64
    Activations Density 0.890%

    No Known Activations