© 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. 13380
    Prev
    Next
    INDEX
    Explanations

    the word "uniform" and sometimes words related to roads or passing, but strongly favors "uniform."

    oai_token-act-pair · gemini-2.0-flash

    uniform

    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
    ^(@)
    -0.98
     aikaa
    -0.94
     vostri
    -0.82
    ++
    -0.81
    berdayakan
    -0.81
    antaranya
    -0.80
     ägg
    -0.80
     leçon
    -0.77
     réactions
    -0.77
     zelve
    -0.77
    POSITIVE LOGITS
    ↵↵
    0.67
     \
    0.59
    %%%%%%%%%%%%%%%%
    0.58
    rente
    0.57
     Gesch
    0.57
    LogFactory
    0.57
    DataContract
    0.55
    tive
    0.53
     (
    0.52
     One
    0.52
    Activations Density 0.422%

    No Known Activations