© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14317
    Prev
    Next
    INDEX
    Explanations

    code snippets or foreign language snippets

    oai_token-act-pair · gemini-2.0-flash

    foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     CreateTagHelper
    -0.53
    ConstraintMaker
    -0.53
     ExecuteAsync
    -0.52
    ChildScrollView
    -0.52
    EndContext
    -0.50
     оригіналу
    -0.47
    assertRaises
    -0.46
    verwijspagina
    -0.45
     AssemblyCompany
    -0.45
    ](#
    -0.45
    POSITIVE LOGITS
     la
    2.64
     las
    1.64
    La
    1.57
     La
    1.50
     los
    1.49
    la
    1.48
     el
    1.31
     LA
    1.26
     les
    1.23
     l
    1.20
    Activations Density 2.360%

    No Known Activations