© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6789
    Prev
    Next
    INDEX
    Explanations

    uses of profanity

    oai_token-act-pair · gemini-2.0-flash

    profanity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     hell
    -1.77
     fuck
    -1.63
     shit
    -1.54
     Hell
    -1.43
    Hell
    -1.42
     damn
    -1.38
    Shit
    -1.38
     HELL
    -1.38
    fuck
    -1.35
     Fuck
    -1.33
    POSITIVE LOGITS
     auffi
    0.61
     للمعارف
    0.61
    RestController
    0.60
     juſ
    0.59
     pleaſure
    0.59
    Życiorys
    0.59
    ariate
    0.58
     juſt
    0.54
    kör
    0.53
     purpoſe
    0.53
    Activations Density 2.802%

    No Known Activations