© 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. 12519
    Prev
    Next
    INDEX
    Explanations

    code elements like numbers and certain punctuation marks

    oai_token-act-pair · gemini-2.0-flash

    Brackets and colons

    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
     betweenstory
    -0.71
     Italijanski
    -0.64
    Autoritní
    -0.56
     >=",
    -0.56
     TextAppearance
    -0.55
     vermelhas
    -0.54
    ysacchar
    -0.54
    IndentedString
    -0.54
    IsMutable
    -0.54
     semej
    -0.54
    POSITIVE LOGITS
    YEN
    0.54
    IsContent
    0.47
     provincial
    0.47
    ydon
    0.44
    клопе
    0.44
    CreateInfo
    0.43
    ("*");
    0.42
    lide
    0.42
    zub
    0.42
     isInitialized
    0.42
    Activations Density 0.192%

    No Known Activations