© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 3938
    Prev
    Next
    INDEX
    Explanations

    opinionated commentary and arguments

    oai_token-act-pair · gemini-2.0-flash

    Controversy and disagreement

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     PRO
    -0.45
     basah
    -0.44
     mathvariant
    -0.43
     Sä
    -0.41
    ob
    -0.39
     کش
    -0.39
    保
    -0.39
    已
    -0.38
    Pro
    -0.38
    逸
    -0.38
    POSITIVE LOGITS
    LookAnd
    0.92
     referenties
    0.89
     nahilalakip
    0.87
     FishBase
    0.87
     ujednoznacz
    0.86
    AccessorTable
    0.84
     Roskov
    0.81
    Бахар
    0.80
    存于互联网档案馆
    0.79
    ViewFeatures
    0.78
    Activations Density 6.132%

    No Known Activations