© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7047
    Prev
    Next
    INDEX
    Explanations

    words associated with principles and integrity

    oai_token-act-pair · gemini-2.0-flash

    character/integrity

    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
     propOrder
    -0.74
    SequentialGroup
    -0.68
    Hozzáférés
    -0.67
     समीक्षाओं
    -0.67
    sizeCache
    -0.67
    artney
    -0.66
    Gambas
    -0.65
     دیکھیے
    -0.64
    DeleteBehavior
    -0.64
    ształ
    -0.61
    POSITIVE LOGITS
     character
    1.28
     Character
    1.17
    character
    1.09
    Character
    1.09
     integrity
    1.09
     honesty
    0.97
     CHARACTER
    0.96
     honest
    0.94
     Honesty
    0.84
    integrity
    0.83
    Activations Density 1.062%

    No Known Activations