© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10785
    Prev
    Next
    INDEX
    Explanations

    Japanese text, specifically the saying "一をいうと十返ってくる"

    oai_token-act-pair · gemini-2.0-flash

    programming/Japanese code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     enfans
    -0.68
     méri
    -0.65
     proprement
    -0.65
     Económica
    -0.64
     peup
    -0.63
     religieux
    -0.63
     réunis
    -0.63
     quæ
    -0.62
     sanitaires
    -0.62
     épu
    -0.62
    POSITIVE LOGITS
    ValueStyle
    0.85
     ModelExpression
    0.84
    AndEndTag
    0.83
    AccessorTable
    0.77
    CloseOperation
    0.74
     mergeFrom
    0.72
     समीक्षाओं
    0.71
    AddHtmlAttribute
    0.70
     виправивши
    0.68
     <",
    0.67
    Activations Density 0.032%

    No Known Activations