© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13970
    Prev
    Next
    INDEX
    Explanations

    words related to scientific experimentation involving titrations and ratios

    oai_token-act-pair · gemini-2.0-flash

    tit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ۣ
    -0.58
     AssemblyCulture
    -0.57
    simpleType
    -0.51
    EndInit
    -0.49
    queryInterface
    -0.47
     FixedUpdate
    -0.47
    Continue
    -0.46
    таратура
    -0.46
    Getenv
    -0.45
     HomeComponent
    -0.44
    POSITIVE LOGITS
    ScopeManager
    0.76
    WithMany
    0.69
    TagMode
    0.68
    جغرافيا
    0.67
    Morfologia
    0.65
    tanleria
    0.63
    CloseOperation
    0.59
    SizeF
    0.59
     surla
    0.59
     للمعارف
    0.58
    Activations Density 2.140%

    No Known Activations