© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16117
    Prev
    Next
    INDEX
    Explanations

    formal language related to finances, institutions, and medicine

    oai_token-act-pair · gemini-2.0-flash

    legal/formal roles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     heh
    -0.49
    className
    -0.47
    da
    -0.44
     Questi
    -0.43
     Feste
    -0.43
    class
    -0.42
    Denne
    -0.42
    RRect
    -0.42
     player
    -0.41
     PLAYER
    -0.41
    POSITIVE LOGITS
    脚注の使い方
    0.73
    ⓧ
    0.69
     disambiguazione
    0.68
    tagHelperRunner
    0.64
    tvguidetime
    0.63
    CodeAttribute
    0.61
    DockStyle
    0.60
     viewDidLoad
    0.60
    servable
    0.59
    RegressionTest
    0.59
    Activations Density 13.295%

    No Known Activations