© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7764
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to legal and medical terminology, often suggesting a discussion of liability, health, or capabilities.

    oai_token-act-pair · gemini-2.0-flash

    formal writing snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     political
    -1.01
    political
    -0.96
    Political
    -0.88
     Political
    -0.87
     POLITICAL
    -0.86
     physical
    -0.85
     sexual
    -0.84
     financial
    -0.81
     linguistic
    -0.81
     emotional
    -0.80
    POSITIVE LOGITS
     operation
    0.59
    AsUp
    0.58
     vulgaires
    0.57
    GEBURTSDATUM
    0.56
    PreferredItem
    0.56
     professionally
    0.55
    Profession
    0.53
     Walkover
    0.52
    честву
    0.52
    ibatis
    0.52
    Activations Density 7.775%

    No Known Activations