© 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. 14603
    Prev
    Next
    INDEX
    Explanations

    scientific units of measure

    oai_token-act-pair · gemini-2.0-flash

    Units of measurement

    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
     contextLoads
    -0.83
    ScopeManager
    -0.81
     snippetHide
    -0.79
     typelib
    -0.79
     houſe
    -0.77
     myſelf
    -0.77
    setVerticalGroup
    -0.76
    netinet
    -0.75
    ^(@)
    -0.75
    localctx
    -0.75
    POSITIVE LOGITS
     and
    0.47
     And
    0.45
    &
    0.42
     ri
    0.41
    ary
    0.41
     n
    0.40
     K
    0.40
    Tran
    0.39
     after
    0.39
     ra
    0.39
    Activations Density 2.374%

    No Known Activations