© 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. 9376
    Prev
    Next
    INDEX
    Explanations

    the word "animation" and variations of it

    oai_token-act-pair · gemini-2.0-flash

    animation

    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
     ModelExpression
    -0.67
    ános
    -0.57
    DOCTYPE
    -0.57
    hrer
    -0.57
     requ
    -0.57
    nalités
    -0.56
     system
    -0.56
    रोध
    -0.56
    nant
    -0.56
    BIÉN
    -0.56
    POSITIVE LOGITS
     sauvages
    1.14
     colorés
    0.89
     asiatique
    0.89
    <bos>
    0.83
     latine
    0.83
     chrétien
    0.83
     sauvage
    0.82
     feroit
    0.80
     nemici
    0.80
     mijne
    0.79
    Activations Density 0.903%

    No Known Activations