© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5666
    Prev
    Next
    INDEX
    Explanations

    words used to describe an organization

    oai_token-act-pair · gemini-2.0-flash

    organizations

    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
    kuuta
    -0.57
     certe
    -0.49
     mid
    -0.49
    చి
    -0.48
     gros
    -0.48
    مص
    -0.48
     pháp
    -0.47
    clerview
    -0.47
    ographi
    -0.47
    NegativeButton
    -0.47
    POSITIVE LOGITS
     raiſ
    0.72
     deſt
    0.67
     itſelf
    0.65
     comigo
    0.65
     Cæsar
    0.63
    Numerology
    0.62
     femininas
    0.62
     uſed
    0.61
     للاسماء
    0.61
     uſ
    0.60
    Activations Density 1.042%

    No Known Activations