© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4933
    Prev
    Next
    INDEX
    Explanations

    technical language related to energy sources and electricity

    oai_token-act-pair · gemini-2.0-flash

    station

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     myſelf
    -0.97
     itſelf
    -0.95
     himſelf
    -0.94
     Monfieur
    -0.89
    ſelves
    -0.88
     autorytatywna
    -0.85
    ſelf
    -0.85
     poffible
    -0.84
     raiſ
    -0.84
     theſe
    -0.84
    POSITIVE LOGITS
     Port
    0.45
    Port
    0.44
     port
    0.43
    HttpPut
    0.40
    ʖ
    0.39
     
    0.38
    Nationalité
    0.38
    インタ
    0.37
     zetten
    0.37
    port
    0.37
    Activations Density 0.320%

    No Known Activations