© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11798
    Prev
    Next
    INDEX
    Explanations

    code snippets with function declarations or calls

    oai_token-act-pair · gemini-2.0-flash

    Parentheses

    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
     purpoſe
    -1.94
     Efq
    -1.92
     houſe
    -1.91
     ſche
    -1.88
     Reſ
    -1.87
     Houſe
    -1.84
     Eſ
    -1.82
     myſelf
    -1.79
     ſeveral
    -1.79
     Jefus
    -1.79
    POSITIVE LOGITS
    )
    1.55
    ),
    1.05
      
    0.98
     
    0.94
     her
    0.90
    ).
    0.88
    ,
    0.87
    ↵
    0.83
     in
    0.83
     for
    0.80
    Activations Density 1.096%

    No Known Activations