© 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
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 12198
    Prev
    Next
    INDEX
    Explanations

    dates or references to specific years

    oai_token-act-pair · gemini-2.0-flash

    Extracted text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    })]
    -0.62
     })}
    -0.56
    MethodImpl
    -0.53
     Familienname
    -0.52
    ()]
    
    -0.51
    )':
    -0.50
    )](
    -0.49
    defineProperty
    -0.49
    typeparam
    -0.49
    ']}
    -0.49
    POSITIVE LOGITS
     تضيفلها
    0.72
    AccessFile
    0.66
     itſelf
    0.63
    BeginContext
    0.63
     päivä
    0.62
    bootstrapcdn
    0.61
    ValueStyle
    0.61
     inoxidable
    0.60
     himſelf
    0.59
     themſelves
    0.57
    Activations Density 1.018%

    No Known Activations