© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10194
    Prev
    Next
    INDEX
    Explanations

    words related to bowel movements, feces, and/or urination

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     nonatomic
    -0.58
    AddTagHelper
    -0.57
    ⓧ
    -0.55
    LayoutConstraint
    -0.54
     saites
    -0.52
    DialogContent
    -0.52
    DotNetBar
    -0.51
     MonoBehaviour
    -0.51
    ExtendWith
    -0.51
    AnchorStyles
    -0.49
    POSITIVE LOGITS
     feces
    0.79
     defec
    0.77
    InitVars
    0.76
     excretion
    0.75
     saliva
    0.75
     poop
    0.70
     excre
    0.67
     excreted
    0.66
     ejac
    0.65
     fecal
    0.65
    Activations Density 0.588%

    No Known Activations