© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11112
    Prev
    Next
    INDEX
    Explanations

    sections of code and LaTeX math notation

    oai_token-act-pair · gemini-2.0-flash

    section

    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
     itſelf
    -2.23
     myſelf
    -2.11
     pleaſure
    -2.11
     purpoſe
    -2.05
     raiſ
    -2.05
     Monfieur
    -2.03
     Theſe
    -2.03
     ſtate
    -2.00
     Efq
    -1.95
     ſeveral
    -1.92
    POSITIVE LOGITS
     
    1.38
    '
    1.36
    ’
    1.35
    .
    1.14
    <eos>
    1.14
      
    1.11
    1.11
    ↵↵
    1.09
    mathrm
    1.07
     P
    1.05
    Activations Density 0.313%
    No Known Activations