© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 942
    Prev
    Next
    INDEX
    Explanations

    this neuron seems to activate on code snippets, math equations, angle brackets, and the letters F and in

    oai_token-act-pair · gemini-2.0-flash

    play

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     كومونز
    -1.04
     propOrder
    -0.93
     }}$}
    -0.85
     שוליים
    -0.77
     Efq
    -0.75
    tlement
    -0.74
    tableFuture
    -0.74
     }}}
    -0.73
    BeginContext
    -0.73
     testSet
    -0.72
    POSITIVE LOGITS
     play
    1.80
     Play
    1.54
    play
    1.54
    Play
    1.46
     PLAY
    1.33
     plays
    1.32
    plays
    1.23
     Plays
    1.23
     played
    1.23
    PLAY
    1.20
    Activations Density 0.654%

    No Known Activations