© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 728
    Prev
    Next
    INDEX
    Explanations

    legal and technical terminology and words that end in "ing," "tion," and "s."

    oai_token-act-pair · gemini-2.0-flash

    technical specifications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ollectionView
    -0.66
     massa
    -0.60
    abestanden
    -0.58
    μάτων
    -0.58
     Annahme
    -0.57
     كومونز
    -0.56
    olah
    -0.56
     messages
    -0.55
     messengers
    -0.55
     Alfaro
    -0.55
    POSITIVE LOGITS
    /*---
    0.64
     Determin
    0.62
     deterministic
    0.60
     specificity
    0.59
     Determine
    0.59
     determin
    0.57
    deterministic
    0.56
     定
    0.55
     Định
    0.55
    定
    0.55
    Activations Density 3.563%

    No Known Activations