© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9755
    Prev
    Next
    INDEX
    Explanations

    mentions of "direction" and "New Zealand."

    oai_token-act-pair · gemini-2.0-flash

    direction

    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
    Negative Logits
     Zealand
    -0.60
    ties
    -0.52
     measurements
    -0.51
    ison
    -0.51
    ?>
    -0.50
     plastique
    -0.43
     fällt
    -0.41
     zealand
    -0.40
    niel
    -0.39
     details
    -0.39
    POSITIVE LOGITS
    GEBURTSDATUM
    1.20
    enumi
    0.98
     nahilalakip
    0.95
    sidemargin
    0.93
    WithIOException
    0.93
    HomeAsUpEnabled
    0.90
    HasForeignKey
    0.86
    EndTag
    0.83
    TypedDataSet
    0.81
    WriteBarrier
    0.76
    Activations Density 1.238%

    No Known Activations