© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14490
    Prev
    Next
    INDEX
    Explanations

    the word "in" or prepositions like "of", "for", "by", "on", with a tendency to activate when these connect to countries, studies, or general topics.

    oai_token-act-pair · gemini-2.0-flash

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     ſtate
    -0.66
     purpoſe
    -0.64
     ſeveral
    -0.64
     ſame
    -0.63
     ویکی‌پدیا
    -0.63
     perſon
    -0.59
     greateſt
    -0.59
     înainte
    -0.59
     becauſe
    -0.58
     Monfieur
    -0.58
    POSITIVE LOGITS
    TypedDataSet
    0.97
    MessageTagHelper
    0.53
    apimachinery
    0.51
     Italijanski
    0.49
    bitur
    0.49
     ExecuteAsync
    0.49
    InjectAttribute
    0.48
    tych
    0.47
    RuleContext
    0.47
     MonoBehaviour
    0.47
    Activations Density 9.667%

    No Known Activations