© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1870
    Prev
    Next
    INDEX
    Explanations

    clauses expressing apology or shame

    oai_token-act-pair · gemini-2.0-flash

    shame

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    mybatisplus
    -0.53
     通販
    -0.46
    ©
    -0.45
     pere
    -0.41
     interest
    -0.41
    athus
    -0.40
     Party
    -0.40
     useSelector
    -0.40
     U
    -0.40
     concern
    -0.39
    POSITIVE LOGITS
     shame
    1.14
    shame
    1.03
     Shame
    0.94
    Shame
    0.93
     ashamed
    0.85
     shameful
    0.84
     فريبيس
    0.82
     honte
    0.81
     disgrace
    0.78
     vergüenza
    0.78
    Activations Density 1.243%

    No Known Activations