© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6906
    Prev
    Next
    INDEX
    Explanations

    the word "jump" in various tenses and forms, sometimes with prepositions or adverbs

    oai_token-act-pair · gemini-2.0-flash

    jump

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    TryGetValue
    -0.67
    PickerController
    -0.63
    ]")]
    -0.63
     UnityEditor
    -0.62
     jspb
    -0.61
    setVerticalGroup
    -0.61
    tagHelperRunner
    -0.60
    webElementXpaths
    -0.60
    ValueStyle
    -0.60
    groupby
    -0.60
    POSITIVE LOGITS
     universitaria
    0.42
    Encyklopedia
    0.41
    Переваги
    0.41
     Universitario
    0.40
    نامه
    0.40
    Studi
    0.39
     Abbey
    0.39
     rings
    0.38
    Agrade
    0.38
     defStyle
    0.38
    Activations Density 1.106%

    No Known Activations