© 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. 9931
    Prev
    Next
    INDEX
    Explanations

    terms related to tables that frequently appear with numbers or that are inside of links

    oai_token-act-pair · gemini-2.0-flash

    Structured data snippets

    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
     myſelf
    -2.78
     Efq
    -2.72
     itſelf
    -2.69
    ſelf
    -2.39
     raiſ
    -2.39
     Monfieur
    -2.38
     Jefus
    -2.36
     Majefty
    -2.36
     Theſe
    -2.34
     Anſ
    -2.27
    POSITIVE LOGITS
     
    1.63
    ↵
    1.46
    ↵↵
    1.45
     (
    1.35
    <eos>
    1.28
     I
    1.24
     and
    1.22
    .
    1.18
    :
    1.17
     The
    1.15
    Activations Density 38.491%

    No Known Activations