© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7025
    Prev
    Next
    INDEX
    Explanations

    java code including the word import and periods following certain letters

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    laceae
    -0.62
    disambiguation
    -0.59
    OOTDTY
    -0.58
    achelors
    -0.56
     l
    -0.56
     menu
    -0.55
    şen
    -0.55
     da
    -0.55
    lusive
    -0.54
    polazione
    -0.54
    POSITIVE LOGITS
    ########.
    0.66
     CreateTagHelper
    0.60
     createState
    0.60
    ंदीखरीदारी
    0.55
     AppBundle
    0.54
    脚注の使い方
    0.52
    ViewFeatures
    0.52
    PerformLayout
    0.51
     PhpStorm
    0.50
     StatelessWidget
    0.50
    Activations Density 0.142%

    No Known Activations