© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8221
    Prev
    Next
    INDEX
    Explanations

    content related to infidelity or betrayal

    oai_token-act-pair · gemini-2.0-flash

    words related to affairs

    np_token-act-pair-logits · gpt-4o-mini

    affair

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     itſelf
    -0.83
     myſelf
    -0.81
    MessageOf
    -0.80
     Theſe
    -0.80
     Houſe
    -0.78
     houſe
    -0.77
     uſed
    -0.71
     Majefty
    -0.71
     poffible
    -0.70
     themſelves
    -0.69
    POSITIVE LOGITS
     affair
    1.29
     affairs
    1.04
     Affair
    1.00
     extra
    0.92
     Affairs
    0.90
    Extra
    0.75
    aff
    0.75
     AFFAIRS
    0.75
     Extra
    0.73
    Aff
    0.73
    Activations Density 1.202%

    No Known Activations