© 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. 6504
    Prev
    Next
    INDEX
    Explanations

    words related to the advantages of using cardiac or mathematical methods

    oai_token-act-pair · gemini-2.0-flash

    benefits and pick

    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
     Efq
    -1.63
     MainAxisSize
    -1.59
     ་་
    -1.50
     Jefus
    -1.46
     snippetHide
    -1.45
     myſelf
    -1.44
    IntoConstraints
    -1.41
     photolibrary
    -1.41
     المعيارى
    -1.40
     ―――――
    -1.37
    POSITIVE LOGITS
    <eos>
    1.13
     
    1.12
      
    0.97
     (
    0.90
    ↵
    0.88
     "
    0.88
     D
    0.84
    ↵↵
    0.82
     -
    0.82
     is
    0.80
    Activations Density 1.293%

    No Known Activations