© 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. 3210
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially in languages like Python, along with related keywords like "class", "import", "def", "command", and annotations.

    oai_token-act-pair · gemini-2.0-flash

    Code configurations

    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
     Offisielt
    -0.93
     pleaſure
    -0.87
    ſelves
    -0.83
     TAMBIÉN
    -0.79
    ſelf
    -0.77
     Reſ
    -0.76
    Життєпис
    -0.75
     Conſ
    -0.75
     disponibilités
    -0.74
     Anſ
    -0.74
    POSITIVE LOGITS
    "}}>
    0.45
    ()];
    0.42
    ">)</
    0.41
    ()])
    0.40
    "}}
    0.40
    "}},
    0.39
    '))
    
    0.39
    ,))
    0.38
    ())
    
    0.38
    __))
    0.38
    Activations Density 30.430%

    No Known Activations