© 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. 14233
    Prev
    Next
    INDEX
    Explanations

    unusual formatting and capitalization, possibly within legal or journalistic texts.

    oai_token-act-pair · gemini-2.0-flash

    archaic/foreign words

    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
    ↵↵
    -0.99
     
    -0.98
    ,
    -0.91
     and
    -0.90
     I
    -0.84
     (
    -0.84
     in
    -0.83
     a
    -0.82
     to
    -0.82
     "
    -0.81
    POSITIVE LOGITS
     Efq
    1.63
     myſelf
    1.61
     itſelf
    1.61
     Monfieur
    1.52
     auffi
    1.45
     pleaſure
    1.45
     raiſ
    1.45
     Majefty
    1.41
     iſt
    1.41
     himſelf
    1.38
    Activations Density 4.535%

    No Known Activations