© 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. 15769
    Prev
    Next
    INDEX
    Explanations

    references to membership in a group or organization

    oai_token-act-pair · gemini-2.0-flash

    member

    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
    WithIOException
    -0.98
     CreateTagHelper
    -0.94
    StoryboardSegue
    -0.93
     beginnetje
    -0.88
     AssemblyCulture
    -0.87
    InputBorder
    -0.87
    MemoryWarning
    -0.84
    HasForeignKey
    -0.82
     mergeFrom
    -0.80
    sizeCache
    -0.79
    POSITIVE LOGITS
     who
    0.43
     történ
    0.39
     -
    0.38
     default
    0.37
    stur
    0.36
    <eos>
    0.36
    воло
    0.35
    ोन
    0.33
     Franklin
    0.33
    underbrace
    0.33
    Activations Density 9.594%

    No Known Activations