© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10630
    Prev
    Next
    INDEX
    Explanations

    the word "before"

    oai_token-act-pair · gemini-2.0-flash

    before

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     before
    -1.76
    before
    -1.67
    Before
    -1.59
     Before
    -1.49
     BEFORE
    -1.40
    BEFORE
    -1.38
     antes
    -1.37
     sebelum
    -1.37
     befo
    -1.27
     înainte
    -1.17
    POSITIVE LOGITS
    rolo
    0.65
    UnitTesting
    0.57
    iastes
    0.57
    bootstrapcdn
    0.56
    protoimpl
    0.52
    тьяна
    0.51
    stylers
    0.51
    蹤
    0.50
     gynnwys
    0.50
    migrationBuilder
    0.49
    Activations Density 0.868%

    No Known Activations