© 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. 3189
    Prev
    Next
    INDEX
    Explanations

    words and abbreviations, particularly within code or technical languages, but also possibly place names and some medical terms.

    oai_token-act-pair · gemini-2.0-flash

    Programming error messages

    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
     semi
    -0.80
     Semi
    -0.77
    semi
    -0.71
    Semi
    -0.71
     sem
    -0.68
     SEMI
    -0.62
     semis
    -0.62
    рных
    -0.57
     Sem
    -0.55
    __).
    -0.54
    POSITIVE LOGITS
     صوتيه
    0.70
     الرياضيه
    0.69
    XmlAccessType
    0.64
    asteroide
    0.63
    elemField
    0.63
     propOrder
    0.61
     ProtoMessage
    0.61
    ыгана
    0.60
    scriptcase
    0.60
    الحياه
    0.59
    Activations Density 13.395%

    No Known Activations