© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 3868
    Prev
    Next
    INDEX
    Explanations

    terms related to software releases and build pipelines

    oai_token-act-pair · gemini-2.0-flash

    software build

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     صوتيه
    -1.11
    دانشنامهٔ
    -0.87
    parsedMessage
    -0.85
    InputBorder
    -0.84
    Personensuche
    -0.84
     الحره
    -0.82
    पया
    -0.81
     OFDb
    -0.80
    oredCriteria
    -0.79
    DockStyle
    -0.78
    POSITIVE LOGITS
     build
    0.94
    build
    0.89
    Build
    0.86
     builds
    0.85
     Build
    0.84
     BUILD
    0.75
     release
    0.71
    Release
    0.69
    builds
    0.69
     Release
    0.68
    Activations Density 2.187%

    No Known Activations