© 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. 12244
    Prev
    Next
    INDEX
    Explanations

    words associated with societal problems, medical terminology, and negative concepts

    oai_token-act-pair · gemini-2.0-flash

    complex topics

    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
     sonder
    -0.52
    SOUNDBITE
    -0.47
    rrh
    -0.47
     okuyayım
    -0.45
     aportes
    -0.45
     sélections
    -0.45
     riservata
    -0.44
     recourse
    -0.44
     <=",
    -0.44
     Colchester
    -0.43
    POSITIVE LOGITS
    پیوند
    0.58
    UserScript
    0.54
     חיצוניים
    0.53
    HomeAsUpEnabled
    0.53
    ьогодні
    0.53
    Demografia
    0.51
    헌
    0.50
    forChild
    0.49
    manas
    0.49
    ousine
    0.49
    Activations Density 1.105%

    No Known Activations