© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1790
    Prev
    Next
    INDEX
    Explanations

    words associated with negative reactions or consequences and some development/software terms

    oai_token-act-pair · gemini-2.0-flash

    technical concepts or methods

    np_token-act-pair-logits · gpt-4o-mini

    strategies and methods

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     ModelExpression
    -0.75
     avoient
    -0.71
    bbene
    -0.69
     estekak
    -0.64
     ویکی‌پدیا
    -0.64
    Sucesor
    -0.64
     purpoſe
    -0.64
     beſt
    -0.63
     étoient
    -0.62
    loroethene
    -0.62
    POSITIVE LOGITS
     technique
    0.97
     strategy
    0.96
     problem
    0.94
     method
    0.91
     approach
    0.84
     concept
    0.84
     process
    0.83
     situation
    0.82
     program
    0.81
     phenomenon
    0.78
    Activations Density 9.269%

    No Known Activations