© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 716
    Prev
    Next
    INDEX
    Explanations

    words related to agreements and regulations

    oai_token-act-pair · gemini-2.0-flash

    legal/technical documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     mode
    -0.52
    ุ่น
    -0.46
     तै
    -0.46
    ępo
    -0.45
     Opportunity
    -0.45
    tsin
    -0.45
    Opportunity
    -0.44
     opportunity
    -0.43
     дове
    -0.43
     wave
    -0.42
    POSITIVE LOGITS
    Rhestr
    0.79
     Jérusalem
    0.75
    AndEndTag
    0.74
    '},
    0.70
     betweenstory
    0.68
     myſelf
    0.68
     sähkö
    0.66
    '):
    0.66
    WithIOException
    0.66
     himſelf
    0.65
    Activations Density 5.229%

    No Known Activations