© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4736
    Prev
    Next
    INDEX
    Explanations

    the word "or" and some words surrounding it

    oai_token-act-pair · gemini-2.0-flash

    or

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     endregion
    -0.56
    DockStyle
    -0.54
     تضيفلها
    -0.54
    CascadeType
    -0.50
     Infórmanos
    -0.50
    كويكب
    -0.50
    FunctionFlags
    -0.49
    zegor
    -0.49
     Perci
    -0.48
    ьаж
    -0.48
    POSITIVE LOGITS
     or
    1.98
     или
    1.48
     atau
    1.36
     eller
    1.31
    或
    1.26
     hoặc
    1.25
     nebo
    1.23
     alebo
    1.23
    Или
    1.20
    거나
    1.20
    Activations Density 0.658%

    No Known Activations