© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 7927
    Prev
    Next
    INDEX
    Explanations

    occurrences of the words "the", "a" or "to" followed by adjectives, nouns, or gerunds

    oai_token-act-pair · gemini-2.0-flash

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ).}
    -1.02
    .)}
    -1.00
    ."),
    -0.90
    ."],
    -0.90
    >--}}
    -0.90
     }],
    -0.89
     ]
    
    -0.88
    ],
    
    -0.88
    '],
    
    -0.86
    '),
    
    -0.84
    POSITIVE LOGITS
     automatiques
    0.70
     figliu
    0.66
     scolaires
    0.65
     fermés
    0.65
     médicaux
    0.62
     définiti
    0.59
     démocr
    0.56
     aikaa
    0.56
     elettrico
    0.55
     africains
    0.55
    Activations Density 26.563%

    No Known Activations