© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 5193
    Prev
    Next
    INDEX
    Explanations

    reports on American football

    oai_token-act-pair · gemini-2.0-flash

    sports player contracts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Efq
    -0.90
    BufferException
    -0.83
    Hochspringen
    -0.79
    Билгалдахарш
    -0.79
    salms
    -0.79
    balleur
    -0.75
     وتسجيلات
    -0.73
    estinian
    -0.72
    ImageField
    -0.71
     poffe
    -0.70
    POSITIVE LOGITS
    殘
    0.43
    alinga
    0.37
    ussch
    0.36
    残
    0.35
    独
    0.34
    RTLD
    0.32
     piste
    0.32
     jag
    0.32
     
    0.31
     defaultstate
    0.31
    Activations Density 0.943%

    No Known Activations