© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1680
    Prev
    Next
    INDEX
    Explanations

    measurements and/or specifications

    oai_token-act-pair · gemini-2.0-flash

    technical jargon and terms

    np_token-act-pair-logits · gpt-4o-mini

    numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     power
    -0.80
     Power
    -0.68
    power
    -0.65
     POWER
    -0.56
    Power
    -0.56
    的力量
    -0.52
     forces
    -0.52
    DockStyle
    -0.49
     force
    -0.49
     getResources
    -0.49
    POSITIVE LOGITS
     betweenstory
    0.73
     &___
    0.69
     незавершена
    0.65
    NameInMap
    0.60
    WireFormatLite
    0.59
    ollectionView
    0.57
     itſelf
    0.56
    //});
    0.55
    RotationOrder
    0.54
    verwijspagina
    0.54
    Activations Density 0.675%

    No Known Activations