© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10042
    Prev
    Next
    INDEX
    Explanations

    the word "affairs," sometimes in the context of political or organizational entities

    oai_token-act-pair · gemini-2.0-flash

    affairs

    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
     affairs
    -2.58
     Affairs
    -2.41
     AFFAIRS
    -2.06
     affair
    -1.76
     Affair
    -1.65
     affaires
    -1.16
    Aff
    -1.16
    aff
    -1.12
     affaire
    -1.00
     Affaires
    -0.96
    POSITIVE LOGITS
    <bos>
    1.24
    iastes
    0.72
    });*/
    0.68
    )».
    0.66
    ))).
    0.66
    /*
    0.62
    })*/
    0.60
    StoryboardSegue
    0.59
    +:+
    0.58
    "',
    0.57
    Activations Density 2.111%

    No Known Activations