© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2380
    Prev
    Next
    INDEX
    Explanations

    code snippets including array manipulation and plotting function calls

    oai_token-act-pair · gemini-2.0-flash

    words related to programming syntax and data structures

    np_token-act-pair-logits · gpt-4o-mini

    computer code and arrays

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     [
    -0.64
     {
    -0.58
    rån
    -0.55
    {
    -0.55
    \{
    -0.54
    [
    -0.50
     tost
    -0.49
    ',['
    -0.48
     ['
    -0.47
    AutoScaleMode
    -0.47
    POSITIVE LOGITS
     IBOutlet
    0.67
     endfor
    0.61
    ändigkeit
    0.59
     DELHI
    0.59
    addPreferredGap
    0.58
     الاطلاع
    0.58
    ttemberg
    0.57
    arraycopy
    0.56
    tivitas
    0.56
    abetes
    0.55
    Activations Density 2.215%

    No Known Activations