© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12048
    Prev
    Next
    INDEX
    Explanations

    words related to basketball video games like NBA2K

    oai_token-act-pair · gemini-2.0-flash

    terms related to sports or team dynamics

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    bootstrapcdn
    -0.71
    hasMoreElements
    -0.69
    ⓧ
    -0.68
     EconPapers
    -0.68
    sizeCache
    -0.61
    SpringBootTest
    -0.52
    naeus
    -0.50
    SourceChecksum
    -0.50
     allAfrica
    -0.49
    featureID
    -0.49
    POSITIVE LOGITS
     ModelExpression
    0.59
     tackling
    0.56
    DispatchToProps
    0.53
    dirty
    0.53
     Tack
    0.53
    migrationBuilder
    0.52
     tackled
    0.52
     kambing
    0.52
    Vanjske
    0.49
    CppMethod
    0.49
    Activations Density 1.320%

    No Known Activations