© 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. 12031
    Prev
    Next
    INDEX
    Explanations

    references to legal and human rights organizations and concepts

    oai_token-act-pair · gemini-2.0-flash

    prefixes indicating groups or classifications

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

    international human rights law

    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
    ValueStyle
    -0.95
     للاسماء
    -0.90
     gyhoeddwyd
    -0.88
    Personendaten
    -0.86
    ########.
    -0.84
    expandindo
    -0.82
    Personensuche
    -0.81
     fathoms
    -0.79
    Sucesor
    -0.79
    ----</
    -0.78
    POSITIVE LOGITS
     top
    0.47
     pow
    0.45
     m
    0.44
     cl
    0.43
     tr
    0.43
     tre
    0.42
     dos
    0.42
     l
    0.42
     reverse
    0.41
     life
    0.41
    Activations Density 2.009%

    No Known Activations