© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 85
    Prev
    Next
    INDEX
    Explanations

    words related to strong, often negative, emotions, like humiliation, suffering, pain, and judgment.

    oai_token-act-pair · gemini-2.0-flash

    heart

    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
    CodeAttribute
    -0.52
    Externé
    -0.48
     урна
    -0.44
     кӀ
    -0.44
    XmlType
    -0.44
    transQ
    -0.42
     Cosa
    -0.40
    Verses
    -0.39
    getOutputStream
    -0.39
    Defin
    -0.38
    POSITIVE LOGITS
     Мексичка
    0.71
    IContainer
    0.69
     MainAxisSize
    0.68
    SharedDtor
    0.65
    DockStyle
    0.64
    HomeAsUpEnabled
    0.62
    mayın
    0.60
    styleType
    0.59
    RequestParam
    0.57
    Erreferentziak
    0.57
    Activations Density 1.258%

    No Known Activations