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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12275
    Prev
    Next
    INDEX
    Explanations

    words related to ethnic and academic studies

    oai_token-act-pair · gemini-2.0-flash

    cultural/ethnic groups and descent

    np_max-act · gemini-2.0-flash

    descent

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Optimizer
    -0.54
    urons
    -0.54
    COMMERCIAL
    -0.53
     Unicorn
    -0.50
     adult
    -0.49
    acyj
    -0.47
     Insured
    -0.47
    zeitig
    -0.47
    demies
    -0.47
    Clik
    -0.46
    POSITIVE LOGITS
    <bos>
    0.89
     '\\;'
    0.79
    RunAsync
    0.63
    Personendaten
    0.61
     NUKAT
    0.58
    putAll
    0.58
    таратура
    0.54
     لينك
    0.54
    ته
    0.54
    ValueGeneration
    0.53
    Activations Density 1.624%

    No Known Activations