© 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. 13293
    Prev
    Next
    INDEX
    Explanations

    language that shows something could possibly occur

    oai_token-act-pair · gemini-2.0-flash

    down

    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
    +#+
    -0.58
     tịch
    -0.57
     Houſe
    -0.56
     sauvages
    -0.55
    orse
    -0.55
    óbal
    -0.55
     againſt
    -0.52
    MLLoader
    -0.52
     Jefus
    -0.51
     pleaſure
    -0.50
    POSITIVE LOGITS
     down
    1.77
    down
    1.51
    Down
    1.34
     Down
    1.34
     DOWN
    1.30
    DOWN
    1.16
    downs
    1.01
     downs
    0.85
    ダウン
    0.73
     xuống
    0.70
    Activations Density 1.163%

    No Known Activations