© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9846
    Prev
    Next
    INDEX
    Explanations

    descriptive words and section headers

    oai_token-act-pair · gemini-2.0-flash

    our

    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
    abestanden
    -0.48
     dostup
    -0.46
    RectangleBorder
    -0.45
     kabát
    -0.45
     pinulongan
    -0.44
     raggi
    -0.42
     ladr
    -0.42
     normais
    -0.41
     rumahnya
    -0.41
     faibles
    -0.41
    POSITIVE LOGITS
     /\.
    0.64
     tourmaline
    0.60
    ValueStyle
    0.59
     considérons
    0.57
     compass
    0.57
     виправивши
    0.57
     projector
    0.55
    ẵng
    0.55
    typeorm
    0.55
     bidet
    0.54
    Activations Density 20.473%

    No Known Activations