© 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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 6162
    Prev
    Next
    INDEX
    Explanations

    words related to law, courts, judgements, and content on the internet

    oai_token-act-pair · gemini-2.0-flash

    the it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     IT
    -1.71
     THE
    -1.66
    THE
    -1.55
    IT
    -1.44
     ITS
    -1.23
     IS
    -1.02
     THIS
    -0.96
     THEM
    -0.91
    YOUR
    -0.86
    IS
    -0.84
    POSITIVE LOGITS
     it
    1.28
     its
    0.89
     the
    0.87
     It
    0.74
     this
    0.70
    InSection
    0.69
     they
    0.67
     their
    0.65
    '])){
    
    0.65
     pihaknya
    0.64
    Activations Density 0.492%

    No Known Activations