© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3472
    Prev
    Next
    INDEX
    Explanations

    descriptions of decorative or design features of objects

    oai_token-act-pair · gemini-2.0-flash

    design features

    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
    rungsseite
    -0.93
    ValueStyle
    -0.75
     שוליים
    -0.73
    TagMode
    -0.70
    URLException
    -0.69
    ///</
    -0.68
    AnchorStyles
    -0.67
     propOrder
    -0.67
    AnimationsModule
    -0.67
    Viitteet
    -0.66
    POSITIVE LOGITS
     resting
    0.62
     adorn
    0.50
    óch
    0.50
     trône
    0.49
     set
    0.47
     rested
    0.46
    ganti
    0.46
    naments
    0.46
     lendemain
    0.46
     ObjectParameter
    0.45
    Activations Density 3.313%

    No Known Activations