© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15659
    Prev
    Next
    INDEX
    Explanations

    words related to technology like patents or articles or descriptions of inventions and devices.

    oai_token-act-pair · gemini-2.0-flash

    technical jargon

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     débats
    -0.69
     pauvres
    -0.67
     leçons
    -0.66
     détruit
    -0.62
     mauvaises
    -0.60
     lèvres
    -0.59
     vérit
    -0.59
     aveug
    -0.59
     habet
    -0.59
     meubles
    -0.58
    POSITIVE LOGITS
    styleType
    0.71
    oa̍t
    0.71
    lgica
    0.67
    yntaxException
    0.61
     Roskov
    0.59
    APORE
    0.58
    Šaltiniai
    0.58
    ulemon
    0.57
    kind
    0.57
     "..\..\..\
    0.55
    Activations Density 4.052%

    No Known Activations