© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5172
    Prev
    Next
    INDEX
    Explanations

    references to beliefs and/or opinions, especially first-person plural pronouns and related verbs

    oai_token-act-pair · gemini-2.0-flash

    we

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
     оригіналу
    -0.71
    Espèce
    -0.65
    prefixer
    -0.64
    sidemargin
    -0.61
     архивлан
    -0.61
     flyknit
    -0.58
     SEDS
    -0.58
    GEBURTSDATUM
    -0.56
    InstrumentedTest
    -0.56
    ///</
    -0.55
    POSITIVE LOGITS
     we
    0.75
     ourselves
    0.64
     We
    0.63
    We
    0.59
     our
    0.57
     devemos
    0.57
     можем
    0.57
    每个人
    0.55
    私たち
    0.55
    我们
    0.54
    Activations Density 1.401%

    No Known Activations