© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12511
    Prev
    Next
    INDEX
    Explanations

    articles and adjectives in sports-related discussions

    oai_token-act-pair · gemini-2.0-flash

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     للمعارف
    -0.66
    IntoConstraints
    -0.58
    ValueStyle
    -0.57
    CloseOperation
    -0.57
     LUMP
    -0.54
    ьаж
    -0.54
     tkinter
    -0.54
    bootstrapcdn
    -0.52
     InputDecoration
    -0.51
     Indus
    -0.51
    POSITIVE LOGITS
     Fiske
    0.56
     mapStateToProps
    0.55
    imageData
    0.51
     toArray
    0.50
    kowanie
    0.49
     branca
    0.49
    hiki
    0.49
     autorités
    0.48
    matchCondition
    0.48
     المختلف
    0.47
    Activations Density 0.765%

    No Known Activations