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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12505
    Prev
    Next
    INDEX
    Explanations

    technical writing, perhaps about circuit boards, medical tests, or legal proceedings

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     restore
    -0.93
     consider
    -0.91
     compare
    -0.91
     focus
    -0.90
     keep
    -0.89
     connect
    -0.88
     serve
    -0.88
     preserve
    -0.88
     take
    -0.87
     allow
    -0.87
    POSITIVE LOGITS
     nød
    0.64
     démocr
    0.56
     étrangères
    0.55
    httphttps
    0.51
     médicaux
    0.50
     nationaux
    0.50
     mennes
    0.49
     resourceCulture
    0.48
    StoryboardSegue
    0.48
     juridiques
    0.47
    Activations Density 13.416%

    No Known Activations