© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13762
    Prev
    Next
    INDEX
    Explanations

    uses of the word "to" alongside conjunctions and nouns, possibly related to intention and purpose

    oai_token-act-pair · gemini-2.0-flash

    to

    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
     JpaRepository
    -0.68
    apimachinery
    -0.67
     referenties
    -0.64
    Portale
    -0.63
     peindre
    -0.63
    phazard
    -0.62
    elden
    -0.60
    Бахар
    -0.59
    Lycka
    -0.59
     abstrato
    -0.59
    POSITIVE LOGITS
    par
    0.50
    Ap
    0.49
     AssemblyCompany
    0.47
    eap
    0.46
    SourceChecksum
    0.45
    __(/*!
    0.44
     invokingState
    0.43
    ap
    0.43
     par
    0.43
    cellona
    0.43
    Activations Density 1.995%

    No Known Activations