© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10210
    Prev
    Next
    INDEX
    Explanations

    Japanese sentence-ending verbs and auxiliary verbs.

    oai_token-act-pair · gemini-2.0-flash

    Japanese

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    们
    -0.50
    でございます
    -0.47
    です
    -0.46
    かもしれませんが
    -0.45
    ppure
    -0.45
    們
    -0.42
    性を
    -0.42
    ingly
    -0.41
    のかもしれません
    -0.40
    yoruz
    -0.40
    POSITIVE LOGITS
    thâu
    0.90
    ArgsConstructor
    0.87
    <bos>
    0.84
    writeFieldEnd
    0.82
    TagMode
    0.80
    EndProject
    0.80
     AssemblyProduct
    0.77
    migrationBuilder
    0.75
    ValueGeneration
    0.75
     '\\;'
    0.73
    Activations Density 0.526%

    No Known Activations