© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9334
    Prev
    Next
    INDEX
    Explanations

    mentions of cost, manufacturing and lab work, especially in a scientific context

    oai_token-act-pair · gemini-2.0-flash

    cost

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    <bos>
    -0.75
    const
    -0.55
    #
    -0.52
     the
    -0.48
     const
    -0.45
     κ
    -0.45
     –
    -0.45
    -0.44
    rasında
    -0.44
    idenza
    -0.43
    POSITIVE LOGITS
     uſed
    0.93
     quæ
    0.90
    ArgsConstructor
    0.90
     pleaſure
    0.90
     poffible
    0.88
     becauſe
    0.88
     iſt
    0.88
     ſind
    0.87
     ſever
    0.84
     fevere
    0.83
    Activations Density 2.007%
    No Known Activations