© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14408
    Prev
    Next
    INDEX
    Explanations

    periods followed by numbers and code-related terms like import, FTP and io

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     is
    -0.61
     in
    -0.54
     the
    -0.54
     
    -0.54
     it
    -0.52
     “
    -0.50
     I
    -0.50
    <bos>
    -0.49
     one
    -0.49
     The
    -0.49
    POSITIVE LOGITS
     myſelf
    0.97
     Monfieur
    0.83
    ſelves
    0.83
     pleaſure
    0.81
     himſelf
    0.80
     itſelf
    0.80
     poffible
    0.79
     themſelves
    0.79
     ་་
    0.78
    ſelf
    0.78
    Activations Density 2.210%

    No Known Activations