© 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. 6100
    Prev
    Next
    INDEX
    Explanations

    the word "for"

    oai_token-act-pair · gemini-2.0-flash

    specific place names or proper nouns

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

    nonsensical/random text

    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
    cplusplus
    -0.50
     ModelExpression
    -0.49
    SpringBootTest
    -0.48
     بيها
    -0.47
     ThemeData
    -0.47
    HasKey
    -0.46
    \|_{\
    -0.45
    \|_{
    -0.45
    copyWith
    -0.45
    %@",
    -0.44
    POSITIVE LOGITS
     Meksiku
    0.81
     AssemblyCulture
    0.68
    Pfalz
    0.68
    цездатний
    0.68
     étrangère
    0.62
     otomatig
    0.59
    RenderAtEndOf
    0.58
    CodedInputStream
    0.57
     AllMovie
    0.56
    setVerticalGroup
    0.56
    Activations Density 0.314%

    No Known Activations