© 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. 1458
    Prev
    Next
    INDEX
    Explanations

    technical writing related to electromagnetic or light wave communication and data transmission

    oai_token-act-pair · gemini-2.0-flash

    sight

    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
     pleaſure
    -0.97
     Majefty
    -0.87
     reaſon
    -0.87
     greateſt
    -0.87
    MLLoader
    -0.87
     itſelf
    -0.87
     purpoſe
    -0.86
    ſelves
    -0.86
     myſelf
    -0.85
     unſ
    -0.85
    POSITIVE LOGITS
    <bos>
    0.66
    ↵
    0.49
    المشاركات
    0.48
     tr
    0.47
    ?
    0.43
    だろうか
    0.42
     per
    0.41
     se
    0.41
     pa
    0.41
     Co
    0.40
    Activations Density 2.329%

    No Known Activations