© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11685
    Prev
    Next
    INDEX
    Explanations

    HTML or other markup tags containing text or numbers.

    oai_token-act-pair · gemini-2.0-flash

    HTML code

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.85
    GEBURTSDATUM
    -0.81
    PerformLayout
    -0.71
    tagHelperRunner
    -0.71
    KommentareTeilen
    -0.71
     onPostExecute
    -0.68
    MemoryWarning
    -0.67
    setVerticalGroup
    -0.67
     Chwiliwch
    -0.66
     nahilalakip
    -0.66
    POSITIVE LOGITS
    oire
    0.46
    isio
    0.45
     eventdata
    0.44
     gempa
    0.41
    griff
    0.41
    ktur
    0.40
    ault
    0.40
    ara
    0.40
    layui
    0.40
    ician
    0.40
    Activations Density 0.153%

    No Known Activations