© 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. 7728
    Prev
    Next
    INDEX
    Explanations

    the numbers 2, 5, 6, 8, and 9, as well as the word "center".

    oai_token-act-pair · gemini-2.0-flash

    datacenter

    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
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -1.12
    脚注の使い方
    -0.88
    CodedInputStream
    -0.87
     CreateTagHelper
    -0.77
    новниш
    -0.77
     يتيمه
    -0.77
    WebServlet
    -0.73
    CloseOperation
    -0.71
     entanto
    -0.69
    routeProvider
    -0.68
    POSITIVE LOGITS
    ↵↵
    0.53
     Wiese
    0.45
     European
    0.45
    ずる
    0.44
     FALLS
    0.43
     Besar
    0.43
    UnknownFieldSet
    0.43
    European
    0.42
     Groß
    0.42
    LLVM
    0.42
    Activations Density 0.619%

    No Known Activations