© 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. 12476
    Prev
    Next
    INDEX
    Explanations

    the word "versus" and also text related to scientific experiments involving comparisons

    oai_token-act-pair · gemini-2.0-flash

    comparisons

    np_max-act · gemini-2.0-flash

    comparisons

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    الحياه
    -0.71
    SourceChecksum
    -0.67
    complexContent
    -0.66
    ngdoc
    -0.66
    msgSender
    -0.59
    MemoryWarning
    -0.59
     protoimpl
    -0.58
    expandindo
    -0.58
     &___
    -0.57
    stateProvider
    -0.57
    POSITIVE LOGITS
    Manbalar
    0.64
     gonzález
    0.63
    قایناقلار
    0.57
     köln
    0.56
     itſelf
    0.56
     féd
    0.55
     lópez
    0.54
    первых
    0.53
    BufferException
    0.52
    enumi
    0.51
    Activations Density 1.341%

    No Known Activations