© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 892
    Prev
    Next
    INDEX
    Explanations

    instances of the word "to" preceded by a word indicating abundance, contribution, giving, reference, or a destination

    oai_token-act-pair · gemini-2.0-flash

    legal contexts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     Erzb
    -0.58
     oreilles
    -0.53
     difficiles
    -0.53
     buoni
    -0.51
     épaules
    -0.50
     tider
    -0.50
    CompilerServices
    -0.50
     TestBed
    -0.50
     bleue
    -0.49
     brancas
    -0.49
    POSITIVE LOGITS
     disambiguazione
    0.86
    SuccessListener
    0.71
    ChildScrollView
    0.66
    HasForeignKey
    0.66
    PageRoute
    0.66
     betweenstory
    0.65
    StoreMessageInfo
    0.65
    __).
    0.63
     CWE
    0.63
     препратки
    0.62
    Activations Density 1.047%

    No Known Activations