© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7243
    Prev
    Next
    INDEX
    Explanations

    common short words

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     entire
    -0.60
     findings
    -0.59
     eyes
    -0.56
    buttonBar
    -0.55
     original
    -0.54
     total
    -0.54
     consequences
    -0.54
     contents
    -0.54
     signature
    -0.53
     DNA
    -0.52
    POSITIVE LOGITS
     enfans
    0.92
     dieux
    0.79
     avoient
    0.78
     ainfi
    0.77
     soeur
    0.76
     plufieurs
    0.76
     the
    0.75
     prisonniers
    0.73
     vägen
    0.73
     vérit
    0.72
    Activations Density 7.453%

    No Known Activations