© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6759
    Prev
    Next
    INDEX
    Explanations

    articles and adjectives relating to business contracts

    oai_token-act-pair · gemini-2.0-flash

    minute

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    림
    -0.67
     Shades
    -0.66
     arrangement
    -0.66
     Pflanze
    -0.65
     proposal
    -0.64
     Maß
    -0.63
     tuyến
    -0.62
     afspraak
    -0.61
    țiune
    -0.60
     işlem
    -0.60
    POSITIVE LOGITS
     Wikispecies
    0.70
    MessageTagHelper
    0.61
     تضيفلها
    0.60
    GraphicsUnit
    0.56
    ]")]
    0.55
     '\\;'
    0.52
    StackNavigator
    0.49
    NOPQRST
    0.49
    stateProvider
    0.47
    IndentedString
    0.47
    Activations Density 3.085%

    No Known Activations