© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 446
    Prev
    Next
    INDEX
    Explanations

    verbs related to making decisions and having experiences

    oai_token-act-pair · gemini-2.0-flash

    thinking, choosing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    GEBURTSDATUM
    -1.02
    AccessorTable
    -0.85
     AppCompatTheme
    -0.82
    LookAnd
    -0.80
    RegressionTest
    -0.80
    tagHelperRunner
    -0.77
    InjectAttribute
    -0.77
    IUrlHelper
    -0.76
    FunctionFlags
    -0.75
    StructEnd
    -0.74
    POSITIVE LOGITS
    Климат
    0.46
    mű
    0.46
    urgi
    0.44
     Men
    0.44
    ASTE
    0.43
     Gill
    0.43
     стоит
    0.43
     Atem
    0.43
     Speise
    0.42
     Nights
    0.42
    Activations Density 0.701%

    No Known Activations