© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15056
    Prev
    Next
    INDEX
    Explanations

    code snippets; perhaps code syntax, or code keywords

    oai_token-act-pair · gemini-2.0-flash

    non-English words or specialized terms

    np_token-act-pair-logits · gpt-4o-mini

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     
    -0.71
    3
    -0.60
    2
    -0.59
    ]
    -0.57
    4
    -0.57
    id
    -0.56
    é
    -0.56
     ou
    -0.56
     und
    -0.56
    .
    -0.56
    POSITIVE LOGITS
     beginnetje
    0.95
     مشين
    0.95
     سكانية
    0.93
     Мексичка
    0.91
     ویکی‌پدیای
    0.91
     propOrder
    0.90
     itſelf
    0.89
    تقاوى
    0.88
    SBATCH
    0.84
     Theſe
    0.84
    Activations Density 1.137%

    No Known Activations