© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5484
    Prev
    Next
    INDEX
    Explanations

    words that include "we," "my," "newborn","baby," "diaper", and "itself."

    oai_token-act-pair · gemini-2.0-flash

    Self-reference and collective experiences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     itſelf
    -1.94
    ſelf
    -1.91
     pleaſure
    -1.91
     Efq
    -1.88
     ſtate
    -1.84
     purpoſe
    -1.80
     Theſe
    -1.80
     houſe
    -1.76
     $_"
    -1.73
     Jefus
    -1.69
    POSITIVE LOGITS
    '
    1.09
    ,
    1.09
    ’
    1.03
    (
    1.02
    2
    0.99
    3
    0.98
    ↵↵
    0.97
    1
    0.94
     
    0.94
    \
    0.94
    Activations Density 0.828%

    No Known Activations