© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15894
    Prev
    Next
    INDEX
    Explanations

    words and names related to Scandinavian people, places, and language

    oai_token-act-pair · gemini-2.0-flash

    Norwegian names and culture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    expandindo
    -1.05
    AndEndTag
    -1.00
     ciudadana
    -0.98
     चीज़ों
    -0.96
    WebVitals
    -0.90
     nahilalakip
    -0.90
     /\.(
    -0.89
     تانيه
    -0.89
    +#+
    -0.89
     utafitiHapana
    -0.86
    POSITIVE LOGITS
     after
    0.65
     when
    0.50
     time
    0.49
     following
    0.48
     out
    0.48
     next
    0.47
     in
    0.47
     or
    0.46
     at
    0.45
     best
    0.45
    Activations Density 0.227%

    No Known Activations