© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4923
    Prev
    Next
    INDEX
    Explanations

    code snippets and documentation, particularly related to Java/Javascript

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Roskov
    -0.52
     and
    -0.52
     nahilalakip
    -0.47
    mphony
    -0.45
     or
    -0.45
    Initializable
    -0.44
     Abp
    -0.43
     nor
    -0.43
    ujin
    -0.43
    MockBean
    -0.43
    POSITIVE LOGITS
     Efq
    0.75
     Houſe
    0.75
     itſelf
    0.74
    RenderAtEndOf
    0.74
     ſever
    0.73
    parsedMessage
    0.70
    ProgressHUD
    0.68
     ſmall
    0.67
     ſeveral
    0.65
     reaſon
    0.65
    Activations Density 0.805%

    No Known Activations