© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13546
    Prev
    Next
    INDEX
    Explanations

    the word "relations"

    oai_token-act-pair · gemini-2.0-flash

    relation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     relations
    -1.45
     Relations
    -1.41
     relation
    -1.35
     Relation
    -1.28
    Relations
    -1.20
    relation
    -1.20
    relations
    -1.17
     RELATIONS
    -1.13
    Relation
    -1.03
     relationship
    -0.88
    POSITIVE LOGITS
    onViewCreated
    0.83
    Tembelea
    0.73
    queryInterface
    0.70
    ')));
    0.69
     intptr
    0.68
    StoryboardSegue
    0.66
    ])));
    0.66
    )]);
    0.65
     AssemblyCulture
    0.65
    UseVisualStyle
    0.65
    Activations Density 0.348%

    No Known Activations