© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13344
    Prev
    Next
    INDEX
    Explanations

    language related to political corruption and legal proceedings

    oai_token-act-pair · gemini-2.0-flash

    bribes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    <bos>
    -0.79
    StreetMap
    -0.73
    Personensuche
    -0.68
     snippetHide
    -0.67
     utafitiHapana
    -0.65
     intStringLen
    -0.62
    Obrázky
    -0.61
     disambiguazione
    -0.60
     للاسماء
    -0.60
     للمعارف
    -0.60
    POSITIVE LOGITS
    jenih
    0.46
    empêcher
    0.42
     king
    0.42
     BrowserModule
    0.41
    Deny
    0.41
     bribe
    0.41
    nische
    0.40
     lead
    0.40
    éviter
    0.40
    PostMapping
    0.40
    Activations Density 0.754%

    No Known Activations