© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7835
    Prev
    Next
    INDEX
    Explanations

    text related to affirmative action policies in universities

    oai_token-act-pair · gemini-2.0-flash

    race issues

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     racial
    -1.80
     ethnic
    -1.66
     racist
    -1.60
     Racial
    -1.55
     racially
    -1.54
     racism
    -1.52
     Ethnic
    -1.52
    Ethnic
    -1.48
    racial
    -1.41
    ethnic
    -1.38
    POSITIVE LOGITS
    ArgumentParser
    0.57
     nahilalakip
    0.54
    Portale
    0.52
    iastes
    0.51
    memoized
    0.51
    ัติ
    0.51
    marshaller
    0.50
    Personensuche
    0.49
     насељу
    0.49
    WithIOException
    0.48
    Activations Density 3.368%

    No Known Activations