© 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. 2159
    Prev
    Next
    INDEX
    Explanations

    words that appear to be non-English, possibly Croatian, related to confirming accounts and email addresses and also finds acronyms and equations in research papers

    oai_token-act-pair · gemini-2.0-flash

    Foreign language fragments

    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
    MigrationBuilder
    -0.68
    setVerticalGroup
    -0.66
     Référence
    -0.60
    دانشنامهٔ
    -0.58
     ceremony
    -0.55
    username
    -0.51
    colgroup
    -0.50
     formal
    -0.50
    Formal
    -0.50
    Hentet
    -0.50
    POSITIVE LOGITS
    égard
    0.56
     Himo
    0.55
    ttin
    0.54
    marginRight
    0.52
    何度
    0.52
    appartamento
    0.51
     isolato
    0.51
     financières
    0.50
    σαι
    0.50
    poli
    0.49
    Activations Density 17.732%

    No Known Activations