© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7286
    Prev
    Next
    INDEX
    Explanations

    the word "slipped/slip" and its related forms, often in conjunction with prepositions "into," "out", or "away", and sometimes other words related to position.

    oai_token-act-pair · gemini-2.0-flash

    slip

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     intptr
    -0.58
    findpost
    -0.57
    Filmographie
    -0.56
    IBOutlet
    -0.52
    webElementXpaths
    -0.52
     Pellegrini
    -0.50
    aarrggbb
    -0.48
     arşivlendi
    -0.46
     Mundial
    -0.46
     LoggerFactory
    -0.46
    POSITIVE LOGITS
    setViewportView
    0.58
    Демографія
    0.56
    بوابة
    0.54
    angk
    0.52
    ELE
    0.52
    voting
    0.49
    ulon
    0.49
    neth
    0.49
     voting
    0.48
     proceeding
    0.48
    Activations Density 9.622%

    No Known Activations