© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9692
    Prev
    Next
    INDEX
    Explanations

    words and short phrases related to professions and education, and some gibberish related to encoding

    oai_token-act-pair · gemini-2.0-flash

    Technical documentation snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     research
    -1.20
    research
    -1.09
     Research
    -1.08
    Research
    -1.07
     RESEARCH
    -1.03
    RESEARCH
    -0.97
     researcher
    -0.96
     Forschung
    -0.95
     Researcher
    -0.94
    Researcher
    -0.92
    POSITIVE LOGITS
    professional
    0.82
    KURZBESCHREIBUNG
    0.82
    Profession
    0.81
    Professional
    0.80
    Portale
    0.80
     professione
    0.80
     profesion
    0.79
    profession
    0.79
     PROFESSIONAL
    0.78
     Profession
    0.77
    Activations Density 0.300%

    No Known Activations