© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8241
    Prev
    Next
    INDEX
    Explanations

    mentions of people's names, titles, and company positions.

    oai_token-act-pair · gemini-2.0-flash

    co

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     co
    -3.55
     Co
    -3.00
    Co
    -2.83
    co
    -2.59
     CO
    -1.82
    CO
    -1.76
     cof
    -1.69
     coc
    -1.47
     coa
    -1.25
     ко
    -1.24
    POSITIVE LOGITS
     صوتيه
    0.77
    RegressionTest
    0.75
     الحره
    0.73
    TagMode
    0.72
     تانيه
    0.70
    ParallelGroup
    0.67
    scrapy
    0.67
     fubject
    0.66
    học
    0.66
    __':
    0.66
    Activations Density 1.653%

    No Known Activations