© 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. 4964
    Prev
    Next
    INDEX
    Explanations

    words related to work and years of experience

    oai_token-act-pair · gemini-2.0-flash

    biographical descriptions

    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
    findpost
    -0.82
    $}}
    -0.69
     betweenstory
    -0.65
     gamblers
    -0.63
     referees
    -0.62
    developers
    -0.61
     messengers
    -0.60
    managers
    -0.60
    editors
    -0.60
     shoppers
    -0.60
    POSITIVE LOGITS
    GEBURTSDATUM
    0.56
     defaultstate
    0.47
     Standard
    0.43
     object
    0.43
    ogast
    0.41
    Pyx
    0.40
     standard
    0.39
    tal
    0.39
    loài
    0.39
    för
    0.38
    Activations Density 3.225%

    No Known Activations