© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12194
    Prev
    Next
    INDEX
    Explanations

    place names (cities, counties, etc.)

    oai_token-act-pair · gemini-2.0-flash

    Arundel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ích
    -0.46
    velse
    -0.46
     when
    -0.43
     Moser
    -0.42
     great
    -0.42
    bisk
    -0.42
    ùm
    -0.42
     hace
    -0.42
    ーター
    -0.42
    ushka
    -0.41
    POSITIVE LOGITS
    Билгалдахарш
    0.78
     gyhoeddwyd
    0.75
     himſelf
    0.73
     myſelf
    0.72
     itſelf
    0.71
     Majefty
    0.69
     OMITBAD
    0.69
     متعلقه
    0.68
     themſelves
    0.68
     houſe
    0.67
    Activations Density 1.898%

    No Known Activations