© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7355
    Prev
    Next
    INDEX
    Explanations

    apostrophes and related punctuation

    oai_token-act-pair · gemini-2.0-flash

    apostrophe

    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
    Negative Logits
    .
    -1.44
    ,
    -1.41
     
    -1.40
    ↵↵
    -1.14
     (
    -1.13
    <eos>
    -1.09
    ↵
    -1.09
    -
    -1.08
    :
    -1.05
     to
    -1.04
    POSITIVE LOGITS
     myſelf
    2.19
     Efq
    2.05
     photolibrary
    2.05
     ―――――
    2.05
     ſind
    2.05
    ^(@)
    2.03
     doubtnut
    2.02
     itſelf
    1.98
     ་་
    1.95
     iſt
    1.85
    Activations Density 1.589%

    No Known Activations