© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7365
    Prev
    Next
    INDEX
    Explanations

    a mix of seemingly unrelated terms; one possibility is it's looking for markup or code.

    oai_token-act-pair · gemini-2.0-flash

    Applications/Products

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     referenties
    -0.54
     AttributeSet
    -0.51
    Capítulo
    -0.50
    Chapters
    -0.50
    UNCIL
    -0.50
    BagConstraints
    -0.49
    */;
    -0.49
    CppCodeGen
    -0.49
    //
    -0.49
     Summit
    -0.48
    POSITIVE LOGITS
     Food
    0.78
     Gas
    0.66
    Gas
    0.65
    Food
    0.63
     Software
    0.62
     Drug
    0.60
     Music
    0.59
     Computer
    0.57
     Cooking
    0.56
     Commercial
    0.56
    Activations Density 5.239%

    No Known Activations