© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12971
    Prev
    Next
    INDEX
    Explanations

    language related to health problems and death.

    oai_token-act-pair · gemini-2.0-flash

    terms related to illness and health

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

    sickness

    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
     utara
    -0.48
    లాలు
    -0.47
     pezzo
    -0.46
    aj
    -0.45
    َّ
    -0.44
    ez
    -0.43
    olt
    -0.42
     rä
    -0.42
    َّ
    -0.42
    ОВА
    -0.41
    POSITIVE LOGITS
     ill
    1.16
     sick
    0.93
     Ill
    0.91
     ILL
    0.90
    Ill
    0.88
     Sick
    0.82
    Sick
    0.81
    ImageContext
    0.81
     سكانية
    0.78
     SICK
    0.75
    Activations Density 1.278%

    No Known Activations