© 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. 10993
    Prev
    Next
    INDEX
    Explanations

    mentions of doing something, getting forced to do something, some profession, mentions of Kanye West, references to time, or mentions of studying.

    oai_token-act-pair · gemini-2.0-flash

    past events and narratives

    np_max-act · 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
    PreferredItem
    -0.74
     AppBundle
    -0.67
     חיצוניים
    -0.63
     للمعارف
    -0.62
     referenties
    -0.61
    pexpr
    -0.60
    Pyx
    -0.59
    허
    -0.59
     geweest
    -0.58
    NameInMap
    -0.58
    POSITIVE LOGITS
    joba
    0.56
    FlatAppearance
    0.48
    unesse
    0.44
     dikel
    0.43
    IRY
    0.43
    ollary
    0.43
     helyez
    0.42
    hasMany
    0.42
    EObject
    0.41
    人家
    0.39
    Activations Density 13.442%

    No Known Activations