© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8658
    Prev
    Next
    INDEX
    Explanations

    words and phrases that occur in online chats and forums

    oai_token-act-pair · gemini-2.0-flash

    pas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     CreateTagHelper
    -0.49
    ]=>
    -0.46
     Vikipedi
    -0.45
    migrationBuilder
    -0.45
     makeStyles
    -0.44
     تضيفلها
    -0.44
    JNIEnv
    -0.43
    ria
    -0.43
     Wiktionnaire
    -0.42
    WebServlet
    -0.42
    POSITIVE LOGITS
    Geplaatst
    0.67
     maternelle
    0.65
    ﷺ
    0.64
     propOrder
    0.59
    AddTagHelper
    0.58
    LookAnd
    0.57
     JpaRepository
    0.57
    EOD
    0.57
     başına
    0.56
    spania
    0.56
    Activations Density 15.283%

    No Known Activations