© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12375
    Prev
    Next
    INDEX
    Explanations

    words related to computer settings, devices, and software code

    oai_token-act-pair · gemini-2.0-flash

    devices and equipment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     device
    -0.96
    Device
    -0.96
    device
    -0.92
     Device
    -0.90
     devices
    -0.88
     equipment
    -0.84
     Gerät
    -0.83
     DEVICE
    -0.82
    devices
    -0.80
     apparaat
    -0.79
    POSITIVE LOGITS
     فريبيس
    0.65
    getDoctrine
    0.58
    nships
    0.50
     nahilalakip
    0.49
    utivo
    0.46
    AlterField
    0.46
    dders
    0.45
     nhờ
    0.45
     Tri
    0.44
     actionMode
    0.44
    Activations Density 52.158%

    No Known Activations