© 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. 9289
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to marketing, sales, or consumer products, especially highlighting brand names.

    oai_token-act-pair · 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
     فريبيس
    -0.61
    awaiter
    -0.59
     Normdatei
    -0.59
    homonymie
    -0.58
     protoimpl
    -0.56
     gyhoeddwyd
    -0.55
    <bos>
    -0.54
     Roskov
    -0.54
    Související
    -0.52
    afficheront
    -0.52
    POSITIVE LOGITS
    gebob
    0.59
     للاسماء
    0.59
    himu
    0.56
    estacks
    0.56
    odeon
    0.55
     packaged
    0.55
     Abonnez
    0.55
     paquet
    0.54
     packaging
    0.52
    parseFrom
    0.52
    Activations Density 0.409%

    No Known Activations