© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5586
    Prev
    Next
    INDEX
    Explanations

    words related to medicine and technical documentation about product assistance or issues

    oai_token-act-pair · gemini-2.0-flash

    scientific/medical contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Kaynakça
    -0.63
     RouterModule
    -0.62
    ArgumentParser
    -0.62
     שוליים
    -0.60
     للمعارف
    -0.59
    thâu
    -0.59
    
    -0.57
    StoryboardSegue
    -0.56
    ècie
    -0.56
    ibatis
    -0.55
    POSITIVE LOGITS
    ContentLoaded
    0.47
     ComVisible
    0.46
    énus
    0.44
     UITableViewCell
    0.44
    }));
    0.43
     professionali
    0.42
    íticas
    0.42
    XFF
    0.42
    มาะ
    0.41
     Défense
    0.41
    Activations Density 0.896%

    No Known Activations