© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10083
    Prev
    Next
    INDEX
    Explanations

    image file paths ending in ".jpg" or ".png" which contain dimensions/size information

    oai_token-act-pair · gemini-2.0-flash

    Image dimensions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    >{@
    -0.54
    PerformLayout
    -0.50
    ressa
    -0.48
     koy
    -0.46
    OMETRY
    -0.44
    yargs
    -0.44
    wikk
    -0.42
     Gate
    -0.42
    <%@
    -0.42
     étro
    -0.41
    POSITIVE LOGITS
    :✨
    0.78
    ThroughAttribute
    0.75
     يتيمه
    0.66
     '\\;'
    0.58
    UserScript
    0.58
    Jeografia
    0.57
     invokingState
    0.56
    verifyException
    0.55
    ContentAsync
    0.53
     &___
    0.53
    Activations Density 0.267%

    No Known Activations