© 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. 10036
    Prev
    Next
    INDEX
    Explanations

    technical writing related to system design and management in software development as well as business analysis.

    oai_token-act-pair · gemini-2.0-flash

    Code, databases, development

    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
     recepto
    -0.46
     IndexPath
    -0.46
     imputed
    -0.45
    issau
    -0.44
    labili
    -0.44
     saisir
    -0.42
     marti
    -0.42
     lượt
    -0.42
     Huey
    -0.42
     carbone
    -0.42
    POSITIVE LOGITS
    tvguidetime
    0.75
     onData
    0.64
     AssemblyProduct
    0.64
    ellyn
    0.59
    baguna
    0.57
    +#+
    0.57
    httphttps
    0.57
    UTERS
    0.54
     protoimpl
    0.54
    mercial
    0.54
    Activations Density 9.254%

    No Known Activations