© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 2806
    Prev
    Next
    INDEX
    Explanations

    locations in Maine and Massachusetts

    oai_token-act-pair · gemini-2.0-flash

    Legal documents and locations

    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
    Negative Logits
     New
    -0.79
    New
    -0.66
    uxxxx
    -0.64
    GenerationType
    -0.56
    ंदीखरीदारी
    -0.56
    chent
    -0.55
    ValueStyle
    -0.54
    ArgsConstructor
    -0.53
     ModelExpression
    -0.53
    WriteTagHelper
    -0.53
    POSITIVE LOGITS
    ansas
    0.56
    xmlWriter
    0.54
     Sider
    0.53
     raiſ
    0.52
    Afrika
    0.52
     Padang
    0.51
    </caption>
    0.51
    localVar
    0.51
     jaya
    0.51
     Rech
    0.50
    Activations Density 0.255%

    No Known Activations