© 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. 13185
    Prev
    Next
    INDEX
    Explanations

    terms in the context of UK government, Energy companies and Taxes

    oai_token-act-pair · gemini-2.0-flash

    UK news articles

    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
     оригіналу
    -0.87
    httphttps
    -0.86
    Geplaatst
    -0.85
     nakalista
    -0.84
     MainAxisSize
    -0.83
    دانشنامهٔ
    -0.79
    EndInit
    -0.79
    XMLSchema
    -0.79
    RegistryLite
    -0.77
    ArgsConstructor
    -0.77
    POSITIVE LOGITS
     rând
    0.55
     voordeel
    0.43
     Améli
    0.42
     parola
    0.41
     bienvenida
    0.40
     Land
    0.40
     land
    0.38
     señalar
    0.38
     Einsch
    0.36
     mohli
    0.36
    Activations Density 0.605%

    No Known Activations