© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13071
    Prev
    Next
    INDEX
    Explanations

    text related to baby care, particularly diapers and bodily waste

    oai_token-act-pair · gemini-2.0-flash

    gross/disgusting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    Vidite
    -0.87
    uxxxx
    -0.81
    MemoryWarning
    -0.77
     AttributeSet
    -0.77
     Numerade
    -0.77
    
    -0.71
    colgroup
    -0.71
     nakalista
    -0.70
    !*\
    -0.69
    homonymie
    -0.69
    POSITIVE LOGITS
     y
    0.82
     gross
    0.70
     Y
    0.64
     Gross
    0.62
     conditions
    0.51
    gross
    0.50
    Gross
    0.50
     Dis
    0.49
     GROSS
    0.48
     i
    0.47
    Activations Density 2.255%

    No Known Activations