© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6644
    Prev
    Next
    INDEX
    Explanations

    phrases where two things are against each other or next to each other

    oai_token-act-pair · gemini-2.0-flash

    foreign language tokens or keywords

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    MigrationBuilder
    -0.56
    <bos>
    -0.54
     }}"></
    -0.49
    webElementXpaths
    -0.47
     }</
    -0.45
    ///</
    -0.45
    ppelin
    -0.41
    这里是
    -0.41
    CppCodeGen
    -0.41
    ContentLoaded
    -0.40
    POSITIVE LOGITS
     متعلقه
    0.67
     linkovi
    0.63
     unto
    0.62
    PyExc
    0.60
    LikeLike
    0.60
    ต่อ
    0.57
     à
    0.57
    ISME
    0.57
    Soorten
    0.57
    Referencie
    0.57
    Activations Density 3.517%

    No Known Activations