© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14112
    Prev
    Next
    INDEX
    Explanations

    abbreviations for measurements of time, temperature and ratings

    oai_token-act-pair · gemini-2.0-flash

    time and ratings

    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
    Negative Logits
    </td>
    -0.57
     ...
    -0.50
    </i>
    -0.50
    :
    -0.48
    <b>
    -0.48
    #
    -0.45
    oro
    -0.45
    ...
    -0.45
     g
    -0.44
    @
    -0.44
    POSITIVE LOGITS
     pleaſure
    1.08
     myſelf
    0.96
    ValueStyle
    0.94
     ſtate
    0.90
     faſt
    0.88
     purpoſe
    0.88
    drawal
    0.88
     themſelves
    0.88
     reaſon
    0.87
     leaſt
    0.86
    Activations Density 2.063%

    No Known Activations