© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12973
    Prev
    Next
    INDEX
    Explanations

    react native code for rendering lists

    oai_token-act-pair · gemini-2.0-flash

    Code layouts and styling

    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
     myſelf
    -0.83
     pleaſure
    -0.83
    tonode
    -0.81
     Majefty
    -0.81
     purpoſe
    -0.80
     Monfieur
    -0.80
    didSet
    -0.80
     greateſt
    -0.79
    DoubleQuotes
    -0.76
     ſtate
    -0.75
    POSITIVE LOGITS
     smo
    0.41
    etra
    0.38
     gesch
    0.38
     kol
    0.38
     AssemblyCulture
    0.38
     sm
    0.37
    älte
    0.37
     kolo
    0.37
     pon
    0.36
    items
    0.36
    Activations Density 0.274%

    No Known Activations