© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10035
    Prev
    Next
    INDEX
    Explanations

    dialogue in a story, as well as words associated with legal proceedings and testimony.

    oai_token-act-pair · gemini-2.0-flash

    Titles Mr, Mrs, Miss

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     AssemblyCompany
    -0.64
    Бахар
    -0.63
    ثيق
    -0.61
    LLocation
    -0.58
     CreateTagHelper
    -0.57
    WriteTagHelper
    -0.57
    TestingModule
    -0.56
    عارف
    -0.55
    ukone
    -0.55
    ContainerState
    -0.54
    POSITIVE LOGITS
     Mr
    2.52
    Mr
    2.30
     Ms
    2.13
     Mrs
    2.03
    Mrs
    1.88
    Ms
    1.83
     Miss
    1.80
     mr
    1.80
    Miss
    1.61
     mrs
    1.53
    Activations Density 1.161%

    No Known Activations