© 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. 4544
    Prev
    Next
    INDEX
    Explanations

    spanish pronouns and auxiliary verbs

    oai_token-act-pair · gemini-2.0-flash

    me

    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
    XmlAccessType
    -0.60
    agd
    -0.54
    LookAnd
    -0.54
    RegressionTest
    -0.53
    NSYLVANIA
    -0.51
    BrowserModule
    -0.51
    werth
    -0.49
     nouveaux
    -0.49
    참고
    -0.48
     nouveau
    -0.47
    POSITIVE LOGITS
    ViewFeatures
    0.60
     ICollection
    0.58
    createCanvas
    0.56
    nessed
    0.54
     useDispatch
    0.53
     gustó
    0.53
    ThemeOverlay
    0.52
     cuesta
    0.52
     pareció
    0.51
     propOrder
    0.51
    Activations Density 0.725%

    No Known Activations