© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5374
    Prev
    Next
    INDEX
    Explanations

    references to Marvel movies and related concepts

    oai_token-act-pair · gemini-2.0-flash

    Marvel cinematic universe

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    PreferredItem
    -0.71
    ViewFeatures
    -0.69
    TestBed
    -0.68
     useDispatch
    -0.64
    下载附件
    -0.59
    IsMutable
    -0.55
     endblock
    -0.54
     jScrollPane
    -0.53
    :✨
    -0.52
     paramInt
    -0.52
    POSITIVE LOGITS
     thuật
    0.53
    StreetMap
    0.52
     vorbehalten
    0.49
    trường
    0.49
    tection
    0.48
    istoitu
    0.47
     Sociedade
    0.47
    nemia
    0.47
    diğimiz
    0.47
    ETIES
    0.47
    Activations Density 2.359%

    No Known Activations