© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 13180
    Prev
    Next
    INDEX
    Explanations

    code snippets in various programming languages

    oai_token-act-pair · gemini-2.0-flash

    code/technical terms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    //
    -0.48
    }`).
    -0.44
    "]);
    
    -0.43
    _
    
    -0.40
    )•
    -0.40
    "])
    
    -0.40
    ]),
    
    -0.39
    ."]
    -0.38
     },
    
    -0.37
     GeoNames
    -0.37
    POSITIVE LOGITS
    string
    0.84
    color
    0.80
    user
    0.80
    class
    0.78
    video
    0.77
    word
    0.77
    name
    0.77
    key
    0.77
    file
    0.76
    main
    0.76
    Activations Density 18.574%

    No Known Activations