© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11875
    Prev
    Next
    INDEX
    Explanations

    the word "federal"

    oai_token-act-pair · gemini-2.0-flash

    federal

    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
    Not in Any Lists

    No Comments

    Negative Logits
     federal
    -1.81
    federal
    -1.66
    Federal
    -1.63
     Federal
    -1.63
     FEDERAL
    -1.50
    FED
    -0.95
    联邦
    -0.95
     федера
    -0.82
     federally
    -0.76
     Федера
    -0.75
    POSITIVE LOGITS
    ]^{-
    0.72
     AppModule
    0.68
    ollectionView
    0.67
     mattino
    0.63
     صوتيه
    0.63
     mattina
    0.59
    iffa
    0.58
     doméstico
    0.58
    HttpSession
    0.57
    ​—
    0.56
    Activations Density 0.800%

    No Known Activations