© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14064
    Prev
    Next
    INDEX
    Explanations

    information about playing sports at particular schools, especially college

    oai_token-act-pair · gemini-2.0-flash

    competition

    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
     VizieR
    -0.55
     useRouter
    -0.49
     Coaching
    -0.49
    romyalgia
    -0.48
    hipping
    -0.48
     coaching
    -0.47
     Travel
    -0.46
     coaches
    -0.45
     Coaches
    -0.45
     trener
    -0.45
    POSITIVE LOGITS
     compete
    0.87
     competition
    0.72
     competes
    0.71
     competed
    0.71
     competing
    0.70
    competi
    0.66
    competition
    0.66
    Competition
    0.64
     Competition
    0.63
    ]--;
    0.62
    Activations Density 14.716%

    No Known Activations