© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3065
    Prev
    Next
    INDEX
    Explanations

    words and phrases that describe a place, time, or position

    oai_token-act-pair · gemini-2.0-flash

    Time or spatial reference

    np_max-act · gemini-2.0-flash

    say "of" Method used: 2 — because most following tokens are "▁of"

    np_max-act-logits · gpt-5-mini
    Triggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    StructEnd
    -0.92
    ]--;
    -0.88
     scania
    -0.82
    OGND
    -0.81
    endphp
    -0.79
     CiNii
    -0.78
     auffi
    -0.78
     nakalista
    -0.77
     vectorielles
    -0.77
     <>",
    -0.75
    POSITIVE LOGITS
     next
    0.52
    -
    0.49
      
    0.49
     fate
    0.48
     W
    0.47
     de
    0.47
     the
    0.47
    W
    0.46
     
    0.46
    .
    0.46
    Activations Density 1.536%

    No Known Activations