© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 4772
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "Ex" typically followed by punctuation

    oai_token-act-pair · gemini-2.0-flash

    Ex

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    sohn
    -0.56
    enegger
    -0.55
    mopolitan
    -0.55
    uccino
    -0.52
     Paglinawan
    -0.52
    CloseOperation
    -0.49
    jabi
    -0.49
     apie
    -0.49
    ers
    -0.49
    	
    -0.49
    POSITIVE LOGITS
     nôtre
    0.91
    ."));
    0.86
     figliu
    0.86
    !")
    
    0.85
     himſelf
    0.84
     specialises
    0.82
    MigrationBuilder
    0.80
    horabuena
    0.79
     '{@
    0.79
    '));
    
    0.79
    Activations Density 3.751%

    No Known Activations