© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1419
    Prev
    Next
    INDEX
    Explanations

    clusters of words related to government and social control being enacted on groups of people

    oai_token-act-pair · gemini-2.0-flash

    News and politics

    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
    use
    -0.48
    ialmente
    -0.47
     committed
    -0.47
    v
    -0.47
    WithIOException
    -0.46
     Attempt
    -0.45
     AssemblyTitle
    -0.44
     claimed
    -0.44
    +}
    -0.43
    WriteAttribute
    -0.43
    POSITIVE LOGITS
    StoryboardSegue
    0.70
     AppColors
    0.63
    mybatisplus
    0.60
    nodoc
    0.60
     protoimpl
    0.59
     виправивши
    0.59
    GOTREF
    0.56
    HomeAsUpEnabled
    0.56
    ibatis
    0.55
    pointments
    0.54
    Activations Density 7.408%

    No Known Activations