© 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. 12143
    Prev
    Next
    INDEX
    Explanations

    places and teams in a sports context and the relationships between them

    oai_token-act-pair · gemini-2.0-flash

    references to ties or being tied

    np_token-act-pair-logits · gpt-4o-mini

    tie

    np_max-act-logits · gemini-2.0-flash
    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
    getDoctrine
    -0.58
    RefNanny
    -0.57
    AccessorTable
    -0.56
    InternalFrame
    -0.56
     Monfieur
    -0.54
    Personensuche
    -0.54
     depositphotos
    -0.52
    rative
    -0.52
    VYMaps
    -0.51
    inafter
    -0.51
    POSITIVE LOGITS
     tied
    1.25
     tying
    1.12
     tie
    1.04
     ties
    0.98
     Tied
    0.96
    tied
    0.92
     Tie
    0.91
    Tied
    0.85
    Tie
    0.85
     Ties
    0.83
    Activations Density 1.205%

    No Known Activations