© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7035
    Prev
    Next
    INDEX
    Explanations

    the name of sports teams/organizations in the context of sports games

    oai_token-act-pair · gemini-2.0-flash

    conflict/competition

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    pulumi
    -0.54
    Mutant
    -0.50
    ברת
    -0.49
    SpringBootTest
    -0.47
     gioielli
    -0.46
    rebbero
    -0.46
    brates
    -0.45
     venons
    -0.45
     gefeiert
    -0.45
    igslist
    -0.45
    POSITIVE LOGITS
     duel
    0.94
     match
    0.82
     battle
    0.78
     duels
    0.78
     matchup
    0.76
     rivalry
    0.74
     encounter
    0.74
     clash
    0.72
     confrontation
    0.68
     showdown
    0.66
    Activations Density 1.058%

    No Known Activations