© 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. 5196
    Prev
    Next
    INDEX
    Explanations

    text describing car crashes in some detail

    oai_token-act-pair · gemini-2.0-flash

    road accidents

    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
     Мексичка
    -0.89
    TagMode
    -0.84
     sociaux
    -0.77
    GEBURTSDATUM
    -0.76
    principalColumn
    -0.70
     OnInit
    -0.70
    RegressionTest
    -0.68
    Tikang
    -0.68
    EDEFAULT
    -0.68
    enumii
    -0.66
    POSITIVE LOGITS
     <
    0.42
     (
    0.40
     discou
    0.40
    #
    0.38
     Co
    0.37
     cellpadding
    0.37
     hit
    0.37
    fill
    0.36
     case
    0.35
    oph
    0.35
    Activations Density 1.501%

    No Known Activations