© 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. 12299
    Prev
    Next
    INDEX
    Explanations

    a variety of words related to law, sports and family

    oai_token-act-pair · gemini-2.0-flash

    words with person/role identifiers

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

    say punctuation marks

    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
     performance
    -0.64
     location
    -0.63
     existence
    -0.63
     DNA
    -0.60
     name
    -0.60
     survival
    -0.60
     content
    -0.59
    quard
    -0.59
     cor
    -0.59
     URL
    -0.59
    POSITIVE LOGITS
     zelve
    0.83
     medesimo
    0.75
     pauvreté
    0.75
     dépasse
    0.73
     själva
    0.73
     stesse
    0.72
     fumée
    0.71
     bonté
    0.68
     refroid
    0.67
     igång
    0.67
    Activations Density 2.140%

    No Known Activations