© 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. 15484
    Prev
    Next
    INDEX
    Explanations

    bibliographic information and citations

    oai_token-act-pair · gemini-2.0-flash

    books and editions

    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
    WithIOException
    -0.64
    AxisAlignment
    -0.57
     noqa
    -0.56
     sauvages
    -0.56
     natale
    -0.55
     gloire
    -0.54
     Picchu
    -0.54
     TResult
    -0.53
     Anaconda
    -0.52
    Honor
    -0.52
    POSITIVE LOGITS
    AnchorTagHelper
    0.60
    ]$}
    0.60
    .")
    0.56
    chyma
    0.55
    .}\
    0.54
    "):
    0.53
    "])
    0.52
    ParallelGroup
    0.52
     CreateTagHelper
    0.52
     net
    0.52
    Activations Density 1.006%

    No Known Activations