© 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. 6980
    Prev
    Next
    INDEX
    Explanations

    the chemical symbol for Sodium, "Na", and words that immediately include it

    oai_token-act-pair · gemini-2.0-flash

    na

    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
    toJSONString
    -0.60
    antic
    -0.53
    DockStyle
    -0.52
    __':
    -0.51
     Qu
    -0.50
    
    -0.50
    lös
    -0.49
    matician
    -0.48
    WithIOException
    -0.47
    __":
    -0.47
    POSITIVE LOGITS
     Sycamore
    0.56
     Moors
    0.56
     Económica
    0.53
     Kandy
    0.52
     Depor
    0.52
    Abitanti
    0.51
     Walling
    0.50
     carnal
    0.49
     Diptera
    0.48
     Madura
    0.48
    Activations Density 0.331%

    No Known Activations