© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 3783
    Prev
    Next
    INDEX
    Explanations

    people who are responsible for something, or may be affected by something.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Their
    -0.77
     Their
    -0.76
     their
    -0.71
    their
    -0.69
     They
    -0.68
    AndEndTag
    -0.67
     they
    -0.67
     mereka
    -0.65
     họ
    -0.65
    they
    -0.64
    POSITIVE LOGITS
     his
    0.68
    MigrationBuilder
    0.66
    twimg
    0.60
    himself
    0.59
     himself
    0.59
     seinem
    0.59
    檚
    0.57
     그의
    0.54
     seiner
    0.53
    的他
    0.53
    Activations Density 3.046%

    No Known Activations