© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7046
    Prev
    Next
    INDEX
    Explanations

    German words, especially multiple words in a row

    oai_token-act-pair · gemini-2.0-flash

    multiple languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    发表于
    -0.67
     Мексичка
    -0.63
     createSprite
    -0.60
    cestry
    -0.59
    MessageState
    -0.58
    jątk
    -0.56
    xymatrix
    -0.56
    msgSender
    -0.55
    ToolStripButton
    -0.54
    Santis
    -0.54
    POSITIVE LOGITS
     verge
    0.39
    niająca
    0.39
    Lea
    0.39
    findpost
    0.38
     Empieza
    0.38
    tığı
    0.37
    }{||
    0.36
    sedia
    0.36
     beginnetje
    0.35
     pneus
    0.35
    Activations Density 0.242%

    No Known Activations