© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4256
    Prev
    Next
    INDEX
    Explanations

    non-English language, specifically particle "no" in Japanese and "Mont" in French

    oai_token-act-pair · gemini-2.0-flash

    の

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     its
    -0.90
     dessen
    -0.82
     own
    -0.82
     whose
    -0.78
    Its
    -0.76
     suo
    -0.75
     seu
    -0.74
    Whose
    -0.73
     ihrer
    -0.73
     ihre
    -0.73
    POSITIVE LOGITS
    ();)
    0.56
    "]:
    0.54
    contentLoaded
    0.53
     neutrons
    0.52
    Rüyada
    0.50
    "](
    0.49
    WebServlet
    0.49
    Obrázky
    0.48
     bezeichneter
    0.48
    protoc
    0.48
    Activations Density 0.373%

    No Known Activations