© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14195
    Prev
    Next
    INDEX
    Explanations

    the word "brick" and its plural

    oai_token-act-pair · gemini-2.0-flash

    brick

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     pleaſure
    -1.33
     Monfieur
    -1.21
     avoient
    -1.17
     ſtate
    -1.15
     purpoſe
    -1.11
     reaſon
    -1.09
     varandra
    -1.09
     feroit
    -1.06
     ſever
    -1.06
     auffi
    -1.06
    POSITIVE LOGITS
     ‘
    0.68
     the
    0.67
     des
    0.64
     he
    0.64
     '
    0.63
     “
    0.59
     r
    0.59
     He
    0.59
     to
    0.59
     e
    0.58
    Activations Density 0.786%

    No Known Activations