© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13945
    Prev
    Next
    INDEX
    Explanations

    non-English words or code snippets

    oai_token-act-pair · 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
     
    -0.94
     la
    -0.89
     de
    -0.88
     d
    -0.85
     kon
    -0.82
     les
    -0.81
     en
    -0.80
    ...
    -0.79
     le
    -0.78
     à
    -0.77
    POSITIVE LOGITS
     Efq
    3.02
     Reſ
    2.95
     Monfieur
    2.95
     Anſ
    2.95
     myſelf
    2.89
     pleaſure
    2.86
     Majefty
    2.81
     Houſe
    2.78
     itſelf
    2.78
     ―――――
    2.75
    Activations Density 1.042%

    No Known Activations