© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8003
    Prev
    Next
    INDEX
    Explanations

    numbers and related terminology like URLs and percentages

    oai_token-act-pair · gemini-2.0-flash

    citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    <bos>
    -0.71
     &
    -0.35
     is
    -0.34
     and
    -0.34
    往
    -0.33
    l
    -0.32
    FormBuilder
    -0.32
    id
    -0.32
    -
    -0.32
     my
    -0.32
    POSITIVE LOGITS
     كومونز
    0.87
    ^(@)
    0.80
     Monfieur
    0.73
     للاسماء
    0.72
    UrlResolution
    0.70
    醐
    0.70
     незавершена
    0.68
     للمعارف
    0.67
     myſelf
    0.67
     Efq
    0.67
    Activations Density 0.648%

    No Known Activations