© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13646
    Prev
    Next
    INDEX
    Explanations

    things related to American football teams and sports analysis

    oai_token-act-pair · gemini-2.0-flash

    sports

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     team
    -2.23
     teams
    -2.11
    team
    -1.93
     Team
    -1.91
     Teams
    -1.84
    Team
    -1.82
    Teams
    -1.75
    teams
    -1.73
    TEAM
    -1.60
     TEAM
    -1.59
    POSITIVE LOGITS
     ſtate
    0.84
     houſe
    0.81
     ſmall
    0.79
     uſ
    0.79
     purpoſe
    0.79
    moiselle
    0.77
    protoimpl
    0.74
    InjectAttribute
    0.74
     ſtre
    0.73
     faſt
    0.73
    Activations Density 1.292%

    No Known Activations