© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15487
    Prev
    Next
    INDEX
    Explanations

    Java code

    oai_token-act-pair · gemini-2.0-flash

    code formatting or structure

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

    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_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
    Negative Logits
     myſelf
    -1.10
     Мексичка
    -1.09
     contextLoads
    -1.07
     itſelf
    -1.05
     HasFactory
    -1.05
    afficheront
    -1.05
     ExecuteAsync
    -1.03
    contentLoaded
    -1.03
    ConstraintMaker
    -1.02
    NUMX
    -1.02
    POSITIVE LOGITS
        
    0.69
    2
    0.62
     
    0.61
    ↵
    0.59
          
    0.57
    ?
    0.56
       
    0.56
            
    0.56
    ↵↵
    0.54
    0.54
    Activations Density 3.881%

    No Known Activations