© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1803
    Prev
    Next
    INDEX
    Explanations

    numerical rankings

    np_token-act-pair-logits · gpt-4o-mini

    mentions of rankings and the number one

    oai_token-act-pair · gemini-2.0-flash

    rankings and numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     GenerationType
    -0.70
    TypedDataSet
    -0.66
     TestBed
    -0.59
    Diweddarwch
    -0.59
    PropertyChanging
    -0.59
    +#+#
    -0.55
    AsUp
    -0.55
    CompilerServices
    -0.55
    addCriterion
    -0.54
    Географиясе
    -0.52
    POSITIVE LOGITS
     cauſe
    0.55
     Celui
    0.54
    φό
    0.53
     one
    0.52
     preſent
    0.51
     spørsmål
    0.50
     spørs
    0.50
     Monfieur
    0.50
     ſtate
    0.50
    нусы
    0.49
    Activations Density 1.527%

    No Known Activations