© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3643
    Prev
    Next
    INDEX
    Explanations

    code blocks that use brackets, colons, quotation marks, and operators

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     autorytatywna
    -0.90
    IsMutable
    -0.89
     nahilalakip
    -0.78
    تقاوى
    -0.77
     الرياضيه
    -0.73
     Paglinawan
    -0.73
    Tikang
    -0.71
    ftagPool
    -0.69
    StoryboardSegue
    -0.69
    Geplaatst
    -0.69
    POSITIVE LOGITS
    illie
    0.48
    acke
    0.46
     band
    0.46
    porre
    0.45
     AsyncTask
    0.43
    remia
    0.42
    |
    0.41
     wear
    0.41
    HttpPut
    0.41
    feinander
    0.40
    Activations Density 13.120%

    No Known Activations