© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10641
    Prev
    Next
    INDEX
    Explanations

    text describing a video game character's abilities

    oai_token-act-pair · gemini-2.0-flash

    prefixes or terms related to additions or enhancements

    np_token-act-pair-logits · gpt-4o-mini
    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
     pleaſure
    -0.97
     raiſ
    -0.92
     cauſe
    -0.89
     faſt
    -0.88
     myſelf
    -0.88
     ſtate
    -0.87
     fevere
    -0.87
     leſs
    -0.84
     purpoſe
    -0.80
    berdayakan
    -0.80
    POSITIVE LOGITS
     multi
    0.52
    tagli
    0.46
     finish
    0.45
     du
    0.45
     trades
    0.44
     au
    0.44
     Find
    0.44
    ap
    0.44
    orto
    0.43
    initComponents
    0.43
    Activations Density 1.339%

    No Known Activations