© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12392
    Prev
    Next
    INDEX
    Explanations

    proper nouns (names of people, places, organizations)

    oai_token-act-pair · gemini-2.0-flash

    names of people/companies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    oredCriteria
    -0.64
     lenker
    -0.57
    unknownFields
    -0.56
    inander
    -0.55
    Географиясе
    -0.51
     CreateTagHelper
    -0.50
     meres
    -0.45
     fato
    -0.45
    Cheers
    -0.44
    alisation
    -0.43
    POSITIVE LOGITS
    expandindo
    0.67
     BorderRadius
    0.62
    enderror
    0.59
     Italijanski
    0.59
    antMatchers
    0.57
     Tite
    0.56
     nemico
    0.56
     Pria
    0.54
     épaules
    0.54
    EDEFAULT
    0.54
    Activations Density 0.422%

    No Known Activations