© 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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 12047
    Prev
    Next
    INDEX
    Explanations

    code blocks containing single digit numbers followed by new lines

    oai_token-act-pair · gemini-2.0-flash

    various punctuations or special characters

    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
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -0.59
    principalColumn
    -0.49
    InjectAttribute
    -0.48
    aarrggbb
    -0.48
    ValueStyle
    -0.47
    potranspiration
    -0.46
    Sucesor
    -0.46
     blos
    -0.46
    InputTagHelper
    -0.46
    SBATCH
    -0.45
    POSITIVE LOGITS
     ')
    
    0.62
     tø
    0.61
    الدراسه
    0.59
    かした
    0.59
    ecera
    0.59
     ?></
    0.58
    hofen
    0.58
    μάτων
    0.57
     StatelessWidget
    0.56
    )}}
    0.56
    Activations Density 1.118%

    No Known Activations