© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14727
    Prev
    Next
    INDEX
    Explanations

    snippets from different kinds of documents

    oai_token-act-pair · gemini-2.0-flash

    part, aspect, beginning

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    <unused61>
    -1.08
    <unused62>
    -1.06
    <unused63>
    -1.03
    ↵
    -1.00
    1
    -0.98
    <eos>
    -0.95
     
    -0.94
    <unused60>
    -0.94
    ...
    -0.93
    ↵↵
    -0.91
    POSITIVE LOGITS
     Theſe
    2.00
     Monfieur
    1.90
     Efq
    1.88
     myſelf
    1.84
     itſelf
    1.71
     Мексичка
    1.59
     purpoſe
    1.58
     Anſ
    1.56
     ſeveral
    1.55
     Jefus
    1.54
    Activations Density 12.738%

    No Known Activations