© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9976
    Prev
    Next
    INDEX
    Explanations

    mentions of the Marvel Cinematic Universe or Marvel comics with frequent uses of the words "the", "films", "and", or "Marvel"

    oai_token-act-pair · gemini-2.0-flash

    Films and series (MCU)

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    )|^{
    -0.47
    ]<<
    -0.46
    ритори
    -0.45
     يتيمه
    -0.44
     señ
    -0.44
    emplace
    -0.43
    érias
    -0.42
     pytest
    -0.42
    septic
    -0.41
     esti
    -0.40
    POSITIVE LOGITS
    FileType
    0.59
    verifyException
    0.59
    webElementXpaths
    0.58
    mybatisplus
    0.56
     onBind
    0.56
    AddTagHelper
    0.54
     autorytatywna
    0.52
    extAlignment
    0.52
    hmä
    0.52
     createContext
    0.51
    Activations Density 2.467%

    No Known Activations