© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11918
    Prev
    Next
    INDEX
    Explanations

    references to journalistic publications like newspapers, articles, blog posts, and opinion pieces

    oai_token-act-pair · gemini-2.0-flash

    opinion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     décédé
    -0.44
     v
    -0.42
     ço
    -0.42
     tür
    -0.41
     mayoría
    -0.40
     role
    -0.40
     disparu
    -0.39
     maioria
    -0.39
    asList
    -0.38
     zvuky
    -0.38
    POSITIVE LOGITS
     للمعارف
    0.93
    RenderAtEndOf
    0.75
     initComponents
    0.68
    ftagPool
    0.68
    InjectAttribute
    0.67
     الدولى
    0.65
     useAuth
    0.65
    rubin
    0.65
     ་་
    0.65
    mappedBy
    0.64
    Activations Density 0.519%

    No Known Activations