© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7995
    Prev
    Next
    INDEX
    Explanations

    mentions of sports

    oai_token-act-pair · gemini-2.0-flash

    sport

    np_max-act · gemini-2.0-flash

    ▁sport

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     en
    -0.73
    ,
    -0.73
     (
    -0.71
    .
    -0.71
     R
    -0.69
     real
    -0.69
    </b>
    -0.69
     
    -0.68
    </i>
    -0.67
     cre
    -0.66
    POSITIVE LOGITS
     avoient
    1.86
     feroit
    1.74
     étoit
    1.72
     auroit
    1.71
     étoient
    1.70
     ainfi
    1.63
     vectorielles
    1.63
     Monfieur
    1.58
     enfans
    1.58
     pouvoit
    1.52
    Activations Density 1.852%

    No Known Activations