© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 167
    Prev
    Next
    INDEX
    Explanations

    instances of "Na" which might indicate languages other than English as well as the phrase "on the"

    oai_token-act-pair · 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
    providedIn
    -0.81
    WithMany
    -0.72
    adaptiveStyles
    -0.71
     propOrder
    -0.66
    iteness
    -0.63
     MonoBehaviour
    -0.63
    Geografía
    -0.63
     disambiguazione
    -0.63
    titleMargin
    -0.63
    URLException
    -0.62
    POSITIVE LOGITS
    XmlAccessorType
    0.52
     känd
    0.42
     Auff
    0.40
     собой
    0.40
     Gerais
    0.39
    zijde
    0.38
     يلي
    0.38
    straße
    0.38
     Jugendlichen
    0.37
    Хьажоргаш
    0.37
    Activations Density 0.184%

    No Known Activations