© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12996
    Prev
    Next
    INDEX
    Explanations

    angle brackets, code snippets, and references to other files

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash

    <code>

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    -1.03
     ―――――
    -1.03
     Monfieur
    -1.01
     Anſ
    -0.98
     doubtnut
    -0.94
     itſelf
    -0.91
    ſelves
    -0.91
    ſelf
    -0.91
     Majefty
    -0.91
     photolibrary
    -0.91
    POSITIVE LOGITS
    ↵
    3.45
      
    1.01
    ↵↵↵
    0.99
     
    0.85
    <eos>
    0.84
    "])){
    0.82
    <bos>
    0.75
    ↵↵↵↵
    0.73
    ↵↵↵↵↵
    0.69
    '])){
    0.68
    Activations Density 29.357%

    No Known Activations