© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10213
    Prev
    Next
    INDEX
    Explanations

    numerical codes, particularly those related to computing

    oai_token-act-pair · gemini-2.0-flash

    programming language keywords or terms

    np_token-act-pair-logits · gpt-4o-mini

    code and numbers

    np_max-act-logits · gemini-2.0-flash
    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
     Sitten
    -0.54
    pada
    -0.50
     Оте
    -0.49
    IntoConstraints
    -0.49
    oplayer
    -0.49
     pooling
    -0.45
     klarer
    -0.44
     absten
    -0.44
     Investigaciones
    -0.44
     cuarta
    -0.43
    POSITIVE LOGITS
    saraba
    0.74
    CppMethod
    0.69
     Audiodateien
    0.64
    windowFixed
    0.60
    Билгалдахарш
    0.57
     eighties
    0.56
     الرياضيه
    0.56
     disambiguazione
    0.56
    RetentionPolicy
    0.54
    CodedInputStream
    0.54
    Activations Density 2.135%

    No Known Activations