© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9589
    Prev
    Next
    INDEX
    Explanations

    uses of "reported", "observed", and "seen" in studies or productions

    oai_token-act-pair · gemini-2.0-flash

    observed/seen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     myſelf
    -0.68
     fisica
    -0.57
    EndContext
    -0.56
     ſtate
    -0.54
    Newswire
    -0.54
     houſe
    -0.52
    setVerticalGroup
    -0.52
    urlpatterns
    -0.51
    ſelf
    -0.49
     themſelves
    -0.49
    POSITIVE LOGITS
    WebElementEntity
    0.71
    Gambas
    0.57
     previous
    0.56
     שוליים
    0.56
    fromnode
    0.55
    intios
    0.53
    <bos>
    0.53
    omores
    0.51
     تجمعات
    0.51
    flink
    0.51
    Activations Density 4.989%

    No Known Activations