© 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. 12789
    Prev
    Next
    INDEX
    Explanations

    text from genealogy or family history records

    oai_token-act-pair · gemini-2.0-flash

    family data or research

    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
    $_['
    -0.55
     olympique
    -0.54
     <>",
    -0.52
     Crunchy
    -0.52
    ModelSerializer
    -0.51
    IntoConstraints
    -0.50
     rospy
    -0.47
    esticides
    -0.47
     فريبيس
    -0.46
     greedy
    -0.45
    POSITIVE LOGITS
     abt
    0.58
     initComponents
    0.57
     تانيه
    0.57
     betweenstory
    0.56
     nahilalakip
    0.51
    Демографія
    0.50
     />";
    0.50
     dau
    0.49
     الحره
    0.49
    তথ্যসূত্র
    0.48
    Activations Density 26.993%

    No Known Activations