© 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. 7023
    Prev
    Next
    INDEX
    Explanations

    apostrophes

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ↵
    -1.22
    ↵↵
    -1.18
     
    -1.13
    .
    -1.11
    ,
    -0.98
    <eos>
    -0.95
     (
    -0.93
     -
    -0.84
      
    -0.81
    !
    -0.80
    POSITIVE LOGITS
    ^(@)
    1.77
     myſelf
    1.73
     ་་
    1.68
     Efq
    1.68
     photolibrary
    1.68
     ―――――
    1.67
     betweenstory
    1.66
     doubtnut
    1.61
     itſelf
    1.61
    InjectAttribute
    1.59
    Activations Density 0.910%

    No Known Activations