© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1459
    Prev
    Next
    INDEX
    Explanations

    words related to product improvement, or new technology

    oai_token-act-pair · gemini-2.0-flash

    job titles

    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
     nahilalakip
    -0.63
    
    -0.63
     astronomers
    -0.57
    +#+#
    -0.56
    WithIOException
    -0.56
     veterinarians
    -0.55
     Italijani
    -0.54
     vesicle
    -0.54
     frond
    -0.54
     relato
    -0.53
    POSITIVE LOGITS
     editor
    1.05
     manager
    1.02
     adviser
    0.96
     creator
    0.94
     coordinator
    0.93
     advisor
    0.93
     organizer
    0.90
     recruiter
    0.88
     writer
    0.88
     producer
    0.88
    Activations Density 8.374%

    No Known Activations