© 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
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10047
    Prev
    Next
    INDEX
    Explanations

    words or short phrases related to math, science or computer programming

    oai_token-act-pair · gemini-2.0-flash

    Code-related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    InjectAttribute
    -1.84
     itſelf
    -1.82
     myſelf
    -1.72
     Efq
    -1.71
     Monfieur
    -1.60
     Theſe
    -1.59
     Majefty
    -1.54
     ―――――
    -1.52
     ModelExpression
    -1.49
     Reſ
    -1.49
    POSITIVE LOGITS
     
    0.94
    .
    0.75
    ↵↵
    0.69
    ,
    0.65
     the
    0.65
    ↵
    0.65
     (
    0.65
     v
    0.64
     O
    0.60
     T
    0.60
    Activations Density 53.846%

    No Known Activations