© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11120
    Prev
    Next
    INDEX
    Explanations

    instances of indicating or suggesting a reason, viewpoint, place, or item, in law or writing.

    oai_token-act-pair · gemini-2.0-flash

    say "point"

    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
     riga
    -0.51
     Profiles
    -0.50
    ộn
    -0.50
    AccessorTable
    -0.49
     wireType
    -0.48
    wissenschaften
    -0.48
    tra
    -0.48
    usa
    -0.48
     HomeController
    -0.48
     lugs
    -0.48
    POSITIVE LOGITS
     poi
    0.73
     peint
    0.67
    tagHelperRunner
    0.67
     AspNetCore
    0.66
     Poin
    0.62
     peindre
    0.61
     pints
    0.60
    upuncture
    0.60
    UnitTesting
    0.59
     POI
    0.57
    Activations Density 1.888%

    No Known Activations