© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7682
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to sports and winning

    oai_token-act-pair · gemini-2.0-flash

    Sports

    np_max-act · gemini-2.0-flash

    sports

    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
    }")
    
    -0.98
    $")
    -0.96
    */;
    -0.94
    })*/
    -0.92
     ]
    
    -0.91
     متعلقه
    -0.90
    حياته
    -0.90
    )».
    -0.89
     мәкал
    -0.89
    ')['
    -0.89
    POSITIVE LOGITS
    ↵
    0.81
    ↵↵
    0.73
     golfers
    0.55
     NASCAR
    0.55
     
    0.54
    1
    0.54
     Golf
    0.53
     golfer
    0.52
     inning
    0.51
    2
    0.51
    Activations Density 0.763%

    No Known Activations