© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8173
    Prev
    Next
    INDEX
    Explanations

    years

    oai_token-act-pair · gemini-2.0-flash

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     hiện
    -0.43
    yonel
    -0.42
     Mar
    -0.41
    chevron
    -0.40
    zard
    -0.39
     INTERESAR
    -0.39
    üy
    -0.39
     var
    -0.38
     hết
    -0.37
     berta
    -0.37
    POSITIVE LOGITS
     ModelExpression
    0.77
     Савезне
    0.71
    CodedInputStream
    0.71
    WriteTagHelper
    0.69
    Chham
    0.69
    ImageContext
    0.69
    elemField
    0.69
     itſelf
    0.68
     ComVisible
    0.66
    quakes
    0.66
    Activations Density 0.373%

    No Known Activations