© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3575
    Prev
    Next
    INDEX
    Explanations

    arguments for fiscal conservatism and discussions of US government debt

    oai_token-act-pair · gemini-2.0-flash

    Government programs/regulations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     дописавши
    -0.56
    зулта
    -0.55
    hoot
    -0.50
    ophylla
    -0.49
    ukone
    -0.49
    ứ
    -0.48
     unknownFields
    -0.48
    esModule
    -0.47
    ceum
    -0.47
     sof
    -0.47
    POSITIVE LOGITS
     Medicare
    0.77
     Katrina
    0.72
    StoryboardSegue
    0.71
     EPA
    0.65
    WebElementEntity
    0.64
     OSHA
    0.63
    Medicare
    0.62
    Katrina
    0.60
    出版年
    0.57
     TAR
    0.56
    Activations Density 4.867%

    No Known Activations