© 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. 12458
    Prev
    Next
    INDEX
    Explanations

    words or phrases that describe a state, condition, or action

    oai_token-act-pair · gemini-2.0-flash

    attributes

    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
    '}>
    -0.91
     Paglinawan
    -0.81
     дописавши
    -0.79
    oredCriteria
    -0.77
     TextAppearance
    -0.77
    "}>
    -0.75
    ')):
    -0.75
    '>
    
    -0.75
    ")));
    
    -0.73
    '},
    
    -0.73
    POSITIVE LOGITS
    ,
    0.48
    .
    0.47
    ban
    0.40
     yet
    0.40
     therefore
    0.38
    3
    0.38
     suun
    0.38
     but
    0.38
    1
    0.38
    documentclass
    0.38
    Activations Density 1.095%

    No Known Activations