© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14097
    Prev
    Next
    INDEX
    Explanations

    words related to safety, governmental bodies and legal proceedings

    oai_token-act-pair · gemini-2.0-flash

    legal, government affairs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    fastjson
    -0.74
    SourceChecksum
    -0.63
     EconPapers
    -0.61
     protoimpl
    -0.57
    StackNavigator
    -0.53
    TestingModule
    -0.52
    GOTREF
    -0.52
     useState
    -0.52
    TagHelpers
    -0.51
    ViewInit
    -0.49
    POSITIVE LOGITS
     Efq
    0.94
     myſelf
    0.90
     purpoſe
    0.88
     Shaksp
    0.84
     Monfieur
    0.83
     poffe
    0.81
     poffible
    0.80
     ſeveral
    0.79
     Anſ
    0.78
     auffi
    0.77
    Activations Density 0.525%

    No Known Activations