© 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. 3167
    Prev
    Next
    INDEX
    Explanations

    the word "shape"

    oai_token-act-pair · gemini-2.0-flash

    shape

    np_max-act · gemini-2.0-flash
    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
    ↵
    -1.09
    <eos>
    -0.95
     
    -0.92
     I
    -0.87
     a
    -0.85
    -
    -0.82
    1
    -0.81
    ↵↵
    -0.79
    <b>
    -0.79
     L
    -0.78
    POSITIVE LOGITS
     Efq
    1.74
     itſelf
    1.65
     myſelf
    1.64
     Theſe
    1.63
     Shakspeare
    1.57
     Monfieur
    1.56
    <unused21>
    1.55
    <unused28>
    1.55
    <unused17>
    1.55
    <unused8>
    1.55
    Activations Density 1.755%

    No Known Activations