© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10217
    Prev
    Next
    INDEX
    Explanations

    technical writing that includes instructions and lists, possibly from the internet

    oai_token-act-pair · gemini-2.0-flash

    Inventions and effort

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    ContentAsync
    -0.66
     كومونز
    -0.63
     CreateTagHelper
    -0.55
    FirstResponder
    -0.55
    rrggbb
    -0.54
    ResumeLayout
    -0.53
     geslacht
    -0.52
    Kaynakça
    -0.52
     Normdatei
    -0.51
    Cordialement
    -0.51
    POSITIVE LOGITS
     BorderSide
    0.61
     himo
    0.52
    InputBorder
    0.50
    auce
    0.48
    vignon
    0.48
    互联网档案馆
    0.47
    hoppers
    0.47
    fog
    0.46
    ropolitan
    0.46
     Fog
    0.46
    Activations Density 37.177%

    No Known Activations