© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10754
    Prev
    Next
    INDEX
    Explanations

    the word "in" and words indicating present tense

    oai_token-act-pair · gemini-2.0-flash

    in

    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
    ArgsConstructor
    -0.75
    RenderAtEndOf
    -0.70
    WaitGroup
    -0.68
    ParallelGroup
    -0.65
    الحياه
    -0.64
     '\\;'
    -0.63
     yym
    -0.63
    RunWith
    -0.61
    WireFormatLite
    -0.60
    numerusform
    -0.59
    POSITIVE LOGITS
     in
    0.77
    in
    0.56
     In
    0.52
    In
    0.46
     AssemblyCulture
    0.46
    קישורים
    0.45
    pch
    0.44
    ětí
    0.44
    mány
    0.43
     action
    0.43
    Activations Density 2.003%

    No Known Activations