© 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. 3045
    Prev
    Next
    INDEX
    Explanations

    references to scientific investigations and political concepts

    oai_token-act-pair · gemini-2.0-flash

    large vs. small

    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
    EndGlobalSection
    -0.60
    argout
    -0.60
    WaitGroup
    -0.53
    AddTagHelper
    -0.52
     HasFactory
    -0.51
     varandra
    -0.49
    CardBody
    -0.48
     noDo
    -0.47
     ComVisible
    -0.47
    ########.
    -0.47
    POSITIVE LOGITS
     large
    2.28
     larger
    2.22
     smaller
    2.16
    large
    2.11
    Large
    2.09
    Larger
    2.08
     Smaller
    2.06
     Larger
    2.05
     Large
    2.03
    larger
    2.03
    Activations Density 5.832%

    No Known Activations