© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13261
    Prev
    Next
    INDEX
    Explanations

    HTML markup, possibly mixed with normal prose

    oai_token-act-pair · gemini-2.0-flash

    Code/Structured data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     houſe
    -0.74
     oprot
    -0.73
     purpoſe
    -0.72
     ſta
    -0.69
    Ơ
    -0.63
     leaſt
    -0.63
     ſeveral
    -0.63
     مشين
    -0.62
     verſ
    -0.61
     whoſe
    -0.60
    POSITIVE LOGITS
    getDrawable
    0.52
     век
    0.47
     int
    0.43
    RectangleBorder
    0.43
     prouver
    0.42
    Cyfarwyddwr
    0.42
     torchvision
    0.41
     specchio
    0.39
    Kontrola
    0.39
    Становништво
    0.39
    Activations Density 0.926%

    No Known Activations