© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6426
    Prev
    Next
    INDEX
    Explanations

    words that describe scientific concepts and research, particularly in biology, genetics, and medicine

    oai_token-act-pair · gemini-2.0-flash

    punctuation and formatting characters

    np_token-act-pair-logits · gpt-4o-mini

    Scientific processes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     example
    -2.20
    example
    -1.78
     Example
    -1.58
     Beispiel
    -1.55
     esempio
    -1.52
    Example
    -1.51
     exemple
    -1.50
     exemplo
    -1.49
     instance
    -1.48
     ejemplo
    -1.48
    POSITIVE LOGITS
    ,
    1.67
    ########.
    0.48
     umana
    0.45
    ،
    0.45
     umane
    0.41
     ,
    0.41
     ouverts
    0.40
    ，
    0.40
     indipendente
    0.40
     sibi
    0.39
    Activations Density 5.974%

    No Known Activations