© 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
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6377
    Prev
    Next
    INDEX
    Explanations

    member access operators in what appears to be C++ code

    oai_token-act-pair · gemini-2.0-flash

    full stop

    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
    <eos>
    -1.50
     
    -1.45
    ↵
    -1.31
    _
    -1.24
    ↵↵
    -1.23
    -1.18
    ↵↵↵
    -1.13
    .
    -1.12
     (
    -1.11
     _
    -1.10
    POSITIVE LOGITS
     auffi
    1.91
     myſelf
    1.86
     Efq
    1.86
     pleaſure
    1.85
     photolibrary
    1.81
     itſelf
    1.79
     ainfi
    1.78
     raiſ
    1.73
     ARXIV
    1.72
     feroit
    1.71
    Activations Density 1.512%
    No Known Activations