© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6966
    Prev
    Next
    INDEX
    Explanations

    words related to soccer or general sports, teams, and leagues

    oai_token-act-pair · gemini-2.0-flash

    sports leagues or divisions

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

    Sports leagues

    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
     useRouter
    -0.69
     lenker
    -0.64
    withIdentifier
    -0.63
    TemporalType
    -0.63
    TagHelper
    -0.60
    destroyAll
    -0.59
     backless
    -0.59
    rmtree
    -0.57
    FieldBuilder
    -0.57
     Players
    -0.56
    POSITIVE LOGITS
     Premier
    0.68
     Premiership
    0.60
     NFL
    0.59
     Major
    0.59
     NHL
    0.59
     MLS
    0.58
     Division
    0.55
     Roskov
    0.55
    Premier
    0.53
     National
    0.52
    Activations Density 1.067%

    No Known Activations