© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7934
    Prev
    Next
    INDEX
    Explanations

    a variety of words in different contexts, but with a bias towards scientific, medical, or technical terms expressing a reaction or change.

    oai_token-act-pair · gemini-2.0-flash

    scientific texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    <bos>
    -1.09
    出版年
    -0.79
    GraphicsUnit
    -0.71
    ExtendWith
    -0.68
    onAttach
    -0.60
    verwijspagina
    -0.60
     griega
    -0.57
    Gweler
    -0.57
     Sequelize
    -0.53
    المشاركات
    -0.53
    POSITIVE LOGITS
    acherous
    0.58
     tartalomajánló
    0.57
     AudioSource
    0.56
    בות
    0.55
    ệp
    0.54
    CloseOperation
    0.54
    IVEREF
    0.54
    arcoma
    0.53
     behalf
    0.52
    principalColumn
    0.52
    Activations Density 3.652%

    No Known Activations