© 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. 4871
    Prev
    Next
    INDEX
    Explanations

    medical terms, mathematical formulas, and references to location

    oai_token-act-pair · gemini-2.0-flash

    Short filler words

    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
     ainfi
    -1.57
     Efq
    -1.55
     Monfieur
    -1.50
     myſelf
    -1.49
     ſeveral
    -1.48
     pleaſure
    -1.45
     avoient
    -1.45
     plufieurs
    -1.44
     purpoſe
    -1.42
     Theſe
    -1.41
    POSITIVE LOGITS
     
    1.05
     un
    0.87
     to
    0.82
     S
    0.81
     (
    0.79
     R
    0.78
     in
    0.76
     I
    0.74
    ↵↵
    0.74
     “
    0.73
    Activations Density 8.210%

    No Known Activations