© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13750
    Prev
    Next
    INDEX
    Explanations

    words relating to government and finance

    oai_token-act-pair · gemini-2.0-flash

    government ministers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     pleaſure
    -0.96
     Efq
    -0.93
     Majefty
    -0.93
     betweenstory
    -0.91
     contextLoads
    -0.91
     myſelf
    -0.90
    IsContent
    -0.89
     himſelf
    -0.85
    ſelves
    -0.85
     themſelves
    -0.85
    POSITIVE LOGITS
     عب
    0.35
    ccas
    0.29
     perros
    0.28
    ://$
    0.28
     Select
    0.28
    洛
    0.27
    周
    0.27
    assertSame
    0.27
     sí
    0.27
    Tis
    0.27
    Activations Density 1.653%

    No Known Activations