© 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. 11055
    Prev
    Next
    INDEX
    Explanations

    words and phrases about products used for communication

    oai_token-act-pair · gemini-2.0-flash

    Technical documentation

    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
    enumi
    -0.56
    AndEndTag
    -0.54
    ReusableCell
    -0.52
     délé
    -0.50
     ListTile
    -0.48
    GraphicsUnit
    -0.48
     aDecoder
    -0.48
     démocr
    -0.47
    gradle
    -0.47
    emplace
    -0.47
    POSITIVE LOGITS
    verwijspagina
    0.78
    emlrt
    0.59
    LikeLike
    0.56
    EndGlobalSection
    0.55
     gynhyrchwyd
    0.54
     AssemblyProduct
    0.53
    Pautan
    0.53
    </caption>
    0.52
    -------------</
    0.52
     meet
    0.50
    Activations Density 2.435%

    No Known Activations