© 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
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14357
    Prev
    Next
    INDEX
    Explanations

    words and phrases relating to laws, rules, and legal procedures

    oai_token-act-pair · gemini-2.0-flash

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     deleter
    -0.70
    UnsafeEnabled
    -0.69
     ProtoMessage
    -0.65
    +#+#
    -0.61
     spender
    -0.60
     AssemblyCulture
    -0.60
    extAlignment
    -0.60
     oprot
    -0.59
    تقاوى
    -0.57
    !")
    -0.57
    POSITIVE LOGITS
    <bos>
    0.98
     consultato
    0.64
    InjectAttribute
    0.55
    __':
    0.49
     post
    0.47
     manual
    0.44
    olkata
    0.44
    hander
    0.43
     AssemblyTitle
    0.43
     nakalista
    0.42
    Activations Density 3.903%

    No Known Activations