© 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. 9281
    Prev
    Next
    INDEX
    Explanations

    concepts related to advertising, marketing, or media-related production

    oai_token-act-pair · gemini-2.0-flash

    advertising

    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
     médicaux
    -0.46
    afar
    -0.46
    Ranges
    -0.44
     científicas
    -0.43
    beg
    -0.41
    容
    -0.41
    子的
    -0.40
     var
    -0.40
    子
    -0.40
    role
    -0.40
    POSITIVE LOGITS
    InjectAttribute
    1.13
     Infórmanos
    1.04
     للاسماء
    0.98
     мәкал
    0.93
    SharedDtor
    0.89
     تضيفلها
    0.88
    BufferException
    0.86
    moiselle
    0.86
    évaluateur
    0.86
    iconque
    0.85
    Activations Density 0.168%

    No Known Activations