© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1827
    Prev
    Next
    INDEX
    Explanations

    This neuron seems to activate on a variety of different kinds of words. It's not possible to summarize the behavior in a single sentence.

    oai_token-act-pair · gemini-2.0-flash

    words related to collections or anthologies

    np_token-act-pair-logits · gpt-4o-mini

    collection

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     postale
    -0.44
     gyhoeddwyd
    -0.44
     Bianca
    -0.43
    ⋱
    -0.43
    LookAnd
    -0.43
    getLogger
    -0.42
    formaz
    -0.42
    osene
    -0.42
    setOn
    -0.42
    buz
    -0.42
    POSITIVE LOGITS
     collection
    1.15
     collect
    1.09
     collects
    1.07
     selection
    1.01
     collected
    0.99
     collecting
    0.99
     compilation
    0.98
     collections
    0.97
    Collection
    0.94
     Collection
    0.93
    Activations Density 2.211%

    No Known Activations