© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13222
    Prev
    Next
    INDEX
    Explanations

    news outlets and TV stations

    oai_token-act-pair · gemini-2.0-flash

    News outlets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     Chaucer
    -0.57
    TAGE
    -0.53
     Efq
    -0.52
    ⓧ
    -0.52
    antasy
    -0.51
     mark
    -0.50
     reflex
    -0.49
    ramientas
    -0.49
    хьтан
    -0.49
     useRouter
    -0.49
    POSITIVE LOGITS
    IntoConstraints
    0.81
     FetchType
    0.59
     goû
    0.57
    rungsseite
    0.55
    Hochspringen
    0.52
    Salta
    0.51
    /**
    0.50
    aarrggbb
    0.50
    InSection
    0.49
    routeProvider
    0.49
    Activations Density 0.363%

    No Known Activations